CN111080553A - Picture optimization processing method, device and equipment and readable storage medium - Google Patents
Picture optimization processing method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN111080553A CN111080553A CN201911297408.9A CN201911297408A CN111080553A CN 111080553 A CN111080553 A CN 111080553A CN 201911297408 A CN201911297408 A CN 201911297408A CN 111080553 A CN111080553 A CN 111080553A
- Authority
- CN
- China
- Prior art keywords
- picture
- preset
- target
- optimal
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 182
- 238000003672 processing method Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 68
- 238000012216 screening Methods 0.000 claims description 16
- 238000009432 framing Methods 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 10
- 238000000605 extraction Methods 0.000 description 10
- 230000003321 amplification Effects 0.000 description 7
- 210000004709 eyebrow Anatomy 0.000 description 7
- 238000003199 nucleic acid amplification method Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 230000007704 transition Effects 0.000 description 5
- 238000005452 bending Methods 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 241000226585 Antennaria plantaginifolia Species 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000005282 brightening Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The application discloses a picture optimization processing method, a device, equipment and a readable storage medium, wherein the picture optimization processing method comprises the following steps: the method comprises the steps of obtaining a preset picture to be processed, determining an optimal target in the preset picture to be processed, obtaining a region picture corresponding to the optimal target, optimizing the region picture to obtain an optimized picture, and fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture. The technical problem of poor optimization effect of the optimal target of the image when photographing in the prior art is solved.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image optimization method, an apparatus, a device, and a readable storage medium.
Background
With the rapid development of the intelligent terminal, the photographing function of the intelligent terminal is also more and more powerful, when a user photographs, in order to obtain a better photographing effect, an optimal target is generally identified and selected and optimized, at present, in the prior art, a photographer generally places the selected target at an optimal imaging position by manually moving the intelligent terminal through composition guidance, or places the selected target at the optimal imaging position through rotation of a camera by rotating the camera, so as to obtain the better photographing effect, but when the optimal target is not at the optimal imaging position, the optimization effect on the selected target will be poor, so that the technical problem that the optimization effect of the optimal image target is poor when the user photographs is present in the prior art.
Disclosure of Invention
The application mainly aims to provide a picture optimization processing method, a picture optimization processing device, picture optimization processing equipment and a readable storage medium, and aims to solve the technical problem that in the prior art, when a picture is taken, the optimization effect of an optimal target of the picture is poor.
In order to achieve the above object, an embodiment of the present application provides an image optimization processing method, where the image optimization processing method is applied to an image optimization processing device, and the image optimization processing method includes:
acquiring a preset picture to be processed, and determining an optimal target in the preset picture to be processed;
obtaining a region picture corresponding to the optimal target, and optimizing the region picture to obtain an optimized picture;
and fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture.
Optionally, the obtaining of the region picture corresponding to the optimal target and performing optimization processing on the region picture, where the obtaining of the optimized processed picture includes:
acquiring a target frame corresponding to the optimal target, and determining the geometric center of the target frame;
based on the geometric center, amplifying the target frame by a preset multiple to obtain an amplified target frame;
framing the optimal target through the amplified target frame to obtain a regional picture;
acquiring the actual distortion degree of the regional picture, comparing the actual distortion degree with a preset distortion degree, and when the actual distortion degree is greater than the preset distortion degree, performing distortion removal processing on the regional picture to obtain a distortion removed picture;
and adjusting the undistorted picture by a preset picture optimization algorithm to obtain an optimized picture.
Optionally, the preset picture optimization algorithm comprises a preferred optimization algorithm and other optimization algorithms,
the step of adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized processed picture comprises the following steps:
acquiring an optimal optimization algorithm of the preset picture to be processed, and optimizing the undistorted picture based on the optimal optimization algorithm to obtain the undistorted picture;
and acquiring other preset optimization algorithms, and optimizing the distortion-removed picture again to obtain the optimized picture.
Optionally, the obtaining and presetting other optimization algorithms to optimize the undistorted picture again, and the obtaining the optimized processed picture includes:
acquiring other preset optimization algorithms, and judging whether the optimal target is shielded or not;
when the optimal target is shielded, carrying out shielding removal processing on the optimal target to obtain a shielding removal picture;
and optimizing the target position of the occlusion-removed picture to obtain the optimized picture.
Optionally, the step of fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture includes:
replacing the area range corresponding to the area picture in the optimized picture and the preset picture to be processed;
and performing gradual fusion on the optimized picture and the preset picture to be processed, and adjusting an area which is not replaced in the preset picture to be processed based on the picture characteristics of the optimized picture to obtain a target optimal picture.
Optionally, the step of obtaining a preset to-be-processed picture and determining an optimal target in the preset to-be-processed picture includes:
acquiring a preset picture to be processed, and extracting the characteristics of a candidate target in the preset picture to be processed to obtain the characteristics of the candidate target;
and comparing each candidate target characteristic with a preset optimal target characteristic to determine an optimal target in the preset to-be-processed picture.
Optionally, the step of obtaining a preset to-be-processed picture and determining an optimal target in the preset to-be-processed picture includes:
judging whether the optimal target is the face of an end user, and when the optimal target is the face of the end user, scanning the face of the end user through a preset face unlocking function to obtain the preset optimal target feature;
when the optimal target is not the face of an end user, acquiring a related picture of the optimal target, and extracting a plurality of picture features in the related picture through a preset feature extractor;
and classifying and screening the plurality of picture features to obtain the preset optimal target feature.
Optionally, the step of classifying and screening the plurality of image features to obtain the preset optimal target feature includes:
classifying the plurality of picture features to obtain a plurality of feature sets, wherein the same target in each related picture corresponds to one feature set;
acquiring the quantity of characteristic values in each characteristic set, and determining an optimal characteristic set based on the quantity of the characteristic values;
and analyzing the distribution condition of various characteristic values in the optimal characteristic set to obtain the preset optimal target characteristic.
The present application further provides a picture optimization processing device, where the picture optimization processing device is applied to a picture optimization processing device, and the picture optimization processing device includes:
the determining module is used for acquiring a preset picture to be processed and determining an optimal target in the preset picture to be processed;
the optimization processing module is used for acquiring the area picture corresponding to the optimal target, and performing optimization processing on the area picture to acquire an optimized picture;
the fusion module is used for fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture;
and the output module is used for acquiring the target optimal picture group corresponding to the optimized picture, and arranging and outputting the pictures in the target optimal picture group.
Optionally, the optimization processing module includes:
the determining submodule is used for obtaining a target frame corresponding to the optimal target and determining a geometric center of the target frame;
the amplification sub-module is used for amplifying the target frame by a preset multiple based on the geometric center to obtain an amplified target frame;
the framing submodule is used for framing the optimal target through the amplified target frame to obtain a regional picture;
the distortion removing sub-module is used for acquiring the actual distortion degree of the regional picture, comparing the actual distortion degree with a preset distortion degree, and performing distortion removing processing on the regional picture to obtain a distortion removed picture when the actual distortion degree is greater than the preset distortion degree;
and the optimization submodule is used for adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized picture.
Optionally, the optimization submodule includes:
the optimization unit is used for acquiring the optimal optimization algorithm of the preset to-be-processed picture, and optimizing the undistorted picture based on the optimal optimization algorithm to obtain the undistorted picture;
and the re-optimization unit is used for acquiring and presetting other optimization algorithms, and performing re-optimization on the distortion-removed picture to acquire the optimized picture.
Optionally, the re-optimization unit comprises:
the first judgment subunit is used for acquiring the preset other optimization algorithms and judging whether the optimal target is blocked or not;
the shielding removing subunit is configured to, when the optimal target is shielded, perform shielding removing processing on the optimal target to obtain a shielding removed picture;
and the second judgment subunit is used for optimizing the target position of the occlusion-removed picture to obtain the optimized picture.
Optionally, the fusion module comprises:
a replacement sub-module, configured to replace a region range corresponding to the region picture in the optimized processed picture and the preset to-be-processed picture;
and the gradual change fusion submodule is used for performing gradual change fusion on the optimized picture and the preset picture to be processed, and adjusting the area which is not replaced in the preset picture to be processed based on the picture characteristics of the optimized picture to obtain the target optimal picture.
Optionally, the determining module includes:
the first feature extraction submodule is used for acquiring a preset to-be-processed picture, and performing feature extraction on a candidate target in the preset to-be-processed picture to acquire a candidate target feature;
and the comparison submodule is used for comparing each candidate target characteristic with a preset optimal target characteristic and determining an optimal target in the preset to-be-processed picture.
Optionally, the picture optimization processing apparatus further includes:
the second feature extraction module is used for judging whether the optimal target is the face of the terminal user or not, and when the optimal target is the face of the terminal user, scanning the face of the terminal user through a preset face unlocking function to obtain the preset optimal target feature;
the third feature extraction module is used for acquiring a related picture of the optimal target when the optimal target is not the face of an end user, and extracting a plurality of picture features in the related picture through a preset feature extractor;
and the classification screening module is used for classifying and screening the plurality of picture features to obtain the preset optimal target feature.
Optionally, the classification screening module includes:
the classification submodule is used for classifying the plurality of picture features to obtain a plurality of feature sets, wherein the same target in each related picture corresponds to one feature set;
the screening submodule is used for acquiring the quantity of characteristic values in each characteristic set and determining an optimal characteristic set based on the quantity of the characteristic values;
and the analysis and determination submodule is used for analyzing the distribution condition of various characteristic values in the optimal characteristic set to obtain the preset optimal target characteristic.
The present application further provides an image optimization processing device, where the image optimization processing device includes: the image optimization processing method comprises a memory, a processor and a program of the image optimization processing method stored on the memory and capable of running on the processor, wherein the program of the image optimization processing method can realize the steps of the image optimization processing method when being executed by the processor.
The application also provides a readable storage medium, wherein a program for implementing the picture optimization processing method is stored on the readable storage medium, and when the program for implementing the picture optimization processing method is executed by a processor, the steps of the picture optimization processing method are implemented.
According to the method and the device, a preset picture to be processed is obtained, an optimal target in the preset picture to be processed is determined, then a region picture corresponding to the optimal target is obtained, the region picture is optimized, an optimized picture is obtained, and then the optimized picture and the preset picture to be processed are fused to obtain a target optimal picture. That is, when the optimal target is at any position on the picture, the optimal target is obtained by determining the position of the optimal target on the picture, then obtaining the area picture, optimizing the area picture to obtain an optimized picture, and finally fusing the optimized picture with the preset picture to be processed. That is, in the present application, when the optimal target is not at the optimal imaging position, the optimal target can be obtained by obtaining and optimizing the region picture, and then the optimal target is fused with the preset to-be-processed picture, so that the optimal target in the preset to-be-processed picture is optimized, and the optimal target picture meeting the user's mind can be provided for the user, and therefore, the technical problem of poor optimization effect of the optimal target of the image when the image is taken in the prior art is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a first embodiment of an image optimization processing method according to the present application;
FIG. 2 is a schematic diagram of an image output interface in the image optimization processing method of the present application;
FIG. 3 is a flowchart illustrating a second embodiment of a method for optimizing an image according to the present application;
fig. 4 is a schematic flowchart of a third embodiment of the image optimization processing method according to the present application;
fig. 5 is a schematic device structure diagram of a hardware operating environment related to a method according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
An embodiment of the present application provides an image-based optimization processing method, which is applied to an image-based optimization processing device, and in an embodiment of the image-based optimization processing method, referring to fig. 1, the image-based optimization processing method includes:
step S10, acquiring a preset to-be-processed picture, and determining an optimal target in the preset to-be-processed picture;
in this embodiment, it should be noted that the preset to-be-processed picture may be obtained by taking a picture through a terminal shooting function or extracting the picture from a terminal storage database, where the optimal target is a target having an optimal target feature in the preset to-be-processed picture, where the optimal target feature is a target feature input in advance, and the optimal target includes targets such as a human face, a lake, and a mountain, for example, if the optimal target feature includes a square face, a double eyelid, and a thin lip, a selected target including the optimal target features is matched in the preset to-be-processed picture, and if the selected target includes multiple targets, the multiple targets are screened through a deeper target feature included in the optimal target feature until the optimal target is obtained, where the deeper target feature includes specific position coordinates of the human face, specific position coordinates of the eyes on the human face, and specific position coordinates of the human face, The specific position coordinates of the lips on the face, etc.
The method comprises the steps of obtaining a preset picture to be processed, determining an optimal target in the preset picture to be processed, specifically, obtaining the preset picture to be processed and a preset optimal target feature, searching a selected target in the preset picture to be processed through the preset optimal target feature, obtaining deep layer target features if the selected target comprises a plurality of targets, further screening the selected target to obtain a single selected target, namely, determining the optimal target in the preset picture to be processed.
The steps of acquiring a preset to-be-processed picture and determining an optimal target in the preset to-be-processed picture comprise:
step S11, acquiring a preset to-be-processed picture, and performing feature extraction on a candidate target in the preset to-be-processed picture to acquire a candidate target feature;
in this embodiment, it should be noted that the candidate target refers to a target that is preset in the to-be-processed picture and is of the same kind as the optimal target, and the candidate target includes the optimal target.
Acquiring a preset picture to be processed, performing feature extraction on a candidate target in the preset picture to be processed to acquire a candidate target feature, specifically acquiring the preset picture to be processed, inputting the preset picture to be processed into a preset feature extractor, so as to frame the suspected target in the preset picture to be processed to obtain a candidate target, i.e. to identify the candidate target in the preset picture to be processed, and further to extract the characteristics of the candidate target to obtain the characteristics of the candidate target, it should be noted that the preset feature extractor is a pre-trained model, and the preset feature extractor is related to the type of the optimal target, for example, assuming that the type of the optimal target is a human face, the preset feature extractor is a face feature extractor, the optimal target is a stone, and the preset feature extractor is a stone feature extractor.
Step S12, comparing each candidate target feature with a preset optimal target feature, and determining an optimal target in the preset to-be-processed picture.
In this embodiment, it should be noted that the preset optimal target features include features such as a target color feature and a target shape feature, the preset optimal target features are features of an optimal target input in advance, and the candidate target features are features extracted by a preset feature extractor.
Comparing each candidate target feature with a preset optimal target feature, determining an optimal target in the preset to-be-processed picture, specifically, comparing each candidate target feature with the preset optimal target feature, obtaining a plurality of similarities between each candidate target feature and the preset optimal target feature, judging whether the similarities are greater than a preset similarity threshold value, when the similarities are greater than the preset similarity threshold value, judging that the candidate target is the candidate optimal target, if the number of the candidate optimal targets is 1, the candidate optimal target is the optimal target, and if the number of the candidate optimal targets is multiple, taking the candidate optimal target corresponding to the similarity with the largest value as the optimal target.
Step S20, obtaining a region picture corresponding to the optimal target, and optimizing the region picture to obtain an optimized picture;
in this embodiment, an area picture corresponding to the optimal target is obtained, and the area picture is optimized to obtain an optimized picture, specifically, according to the size of the optimal target in the preset picture to be processed, the size of the optimal target is matched to match a corresponding picture frame, and the size of the picture frame is the size of the optimal target of a preset multiple, and then the optimal target is framed by the picture frame to obtain a framed selection area of the picture frame on the preset picture to be processed, that is, the area picture corresponding to the optimal target, further, the area picture is optimized by a preset optimization algorithm to obtain the optimized picture, wherein the preset optimization algorithm includes distortion removal algorithm, definition adjustment algorithm, light filling algorithm, and other algorithms, further, and combining one or more preset optimization algorithms to obtain various image optimization logics.
Further, the step of obtaining the area picture corresponding to the optimal target, performing optimization processing on the area picture, and obtaining the optimized processed picture further includes:
and D10, acquiring the target optimal picture group corresponding to the optimized picture, and arranging and outputting the pictures in the target optimal picture group.
In this embodiment, it should be noted that the optimized picture is optimized according to a preset picture optimization logic, where the preset picture optimization logic at least includes a first picture optimization logic and a second picture optimization logic.
Acquiring a target optimal picture group corresponding to the optimized picture, arranging and outputting pictures in the target optimal picture group, specifically, replacing the optimized picture with a framing area in a preset picture to be processed, wherein the position and the orientation of the optimized picture on the preset picture to be processed are consistent with the position and the orientation of the framing area, further, setting a transition zone between the optimized picture and an un-replaced area of the preset picture to be processed, wherein the un-replaced area refers to a picture area which does not belong to the framing area on the preset picture to be processed, performing gradual transition on the optimized picture and the un-replaced area, and further performing gradual fusion on the optimized picture and the preset picture to be processed based on a preset gradual change algorithm to obtain the pictures in the target optimal picture group, if the optimized picture is optimized by a first picture optimization logic, a first target optimal picture is obtained, if the optimized picture is optimized by a second picture optimization logic, a second target optimal picture is obtained, further, the first target optimal picture and the second target optimal picture are combined to obtain a target optimal picture group, and further, the target optimal picture group is arranged and output by a picture output interface shown in fig. 2, wherein a preview interface is the target optimal picture selected by a user.
And step S30, fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture.
In this embodiment, the optimized picture and the preset picture to be processed are fused to obtain a target optimal picture, specifically, the optimized picture and a frame selection area in the preset picture to be processed are replaced, wherein, the position and the orientation of the optimized picture on the preset picture to be processed are consistent with the position and the orientation of the frame selection area, setting a transition standby between the optimization processing picture and the non-replacement area of the preset picture to be processed, wherein the non-replacement area refers to an area of a preset picture to be processed, which does not belong to a framing area, and the optimized picture and the non-replacement area are subjected to gradual transition, and then fusing the optimized picture and the preset picture to be processed based on a preset gradient algorithm to obtain a target optimal picture.
The step of fusing the optimized picture and the preset picture to be processed to obtain the target optimal picture comprises the following steps:
step S31, replacing the picture area corresponding to the area picture in the optimized picture and the preset picture to be processed;
in this embodiment, the optimized picture and the picture region corresponding to the region picture in the preset picture to be processed are replaced, specifically, the optimized picture and the frame selection region in the preset picture to be processed are replaced, and the position of the optimized picture on the preset picture to be processed is consistent with the position of the frame selection region.
And step S32, performing gradual fusion on the optimized picture and the preset picture to be processed, and adjusting the area which is not replaced in the preset picture to be processed based on the picture characteristics of the optimized picture to obtain the target optimal picture.
In this embodiment, the optimized picture and the preset picture to be processed are gradually fused, an undisplaced region in the preset picture to be processed is adjusted based on the picture characteristics of the optimized picture, so as to obtain a target optimal picture, specifically, a transition standby is set between the optimized picture and the undisplaced region of the preset picture to be processed, the optimized picture and the undisplaced region are gradually transitioned, the optimized picture and the preset picture to be processed are fused based on a preset gradual change algorithm, so as to obtain a fused picture, and further, the picture characteristics of the optimized picture are based on the picture characteristics of the optimized picture, wherein the picture characteristics include color, exposure, resolution, and the like, the undisplaced region in the preset picture to be processed is adjusted, so that the picture characteristics of the undisplaced region are consistent with the picture characteristics of the optimized picture, and further obtaining a target optimal picture.
In the embodiment, a preset to-be-processed picture is obtained, an optimal target in the preset to-be-processed picture is determined, then a region picture corresponding to the optimal target is obtained, the region picture is optimized to obtain an optimized picture, and the optimized picture and the preset to-be-processed picture are fused to obtain a target optimal picture. That is, when the optimal target is at any position on the picture, the embodiment obtains the region picture by determining the position of the optimal target on the picture, performs optimization processing on the region picture to obtain an optimized picture, and finally performs fusion of the optimized picture and the preset picture to be processed to obtain the target optimal picture. That is, in this embodiment, when the optimal target is not at the optimal imaging position, the optimal target picture can be obtained by obtaining and optimizing the region picture, and then the optimal target picture is fused with the preset to-be-processed picture, so that the optimal target in the preset to-be-processed picture is optimized, and further the optimal target picture meeting the mind of the user can be provided to the user, and therefore, the technical problem that the optimal target of the image is poor in optimization effect when the image is taken in the prior art is solved.
Further, referring to fig. 3, based on the first embodiment in the present application, in another embodiment of the image optimization processing method, the step of obtaining an optimized processed image by obtaining a region image corresponding to the optimal target and performing optimization processing on the region image includes:
step S21, obtaining a target frame corresponding to the optimal target, and determining the geometric center of the target frame;
in this embodiment, a target frame corresponding to the optimal target is obtained, and a geometric center of the target frame is determined, specifically, a target size of the optimal target on a preset to-be-processed picture is obtained, and a rectangular target frame corresponding to the optimal target is matched based on the target size, where the optimal target is in the rectangular target frame, and the rectangular target frame is a rectangular frame with a smallest area determined according to a boundary point of the optimal target.
Step S22, based on the geometric center, amplifying the target frame by a preset multiple to obtain an amplified target frame;
in this embodiment, based on the geometric center, the target frame is amplified by a preset multiple to obtain an amplified target frame, and specifically, based on the geometric center, the target frame is amplified by a preset multiple to obtain an amplified target frame, where the geometric center of the amplified target frame and the geometric center of the target frame are set by a user or a default multiple of the preset multiple is used.
Step S23, framing the optimal target through the amplified target frame to obtain a region picture;
in this embodiment, the optimal target is framed by the enlarged target frame, and a region picture is obtained, specifically, framing the optimal target by the amplification target frame, judging whether the boundary of the amplification target frame exceeds the boundary of the preset picture to be processed or not, if the boundary of the amplification target frame does not exceed the boundary of the preset picture to be processed, the picture area framed by the amplifying frame is the area picture, if the boundary of the amplifying target frame exceeds the boundary of the preset picture to be processed, based on the geometric center, reducing the enlarged target frame until the reduced enlarged target frame is within a preset picture range to be processed, and the boundary of the reduced amplified target frame is overlapped with the boundary of the preset picture to be processed, and the area framed by the reduced amplified target frame is the area picture.
Step S24, acquiring the actual distortion degree of the area picture, comparing the actual distortion degree with a preset distortion degree, and when the actual distortion degree is larger than the preset distortion degree, performing distortion removal processing on the area picture to obtain a distortion removal picture;
in this embodiment, it should be noted that the distortion refers to a straight line outside a main axis in the object plane, and is a curved line after being imaged by the optical system, an imaging error of the optical system is referred to as distortion, where the distortion includes pincushion distortion, barrel distortion, and linear distortion, and an actual distortion degree of the area picture is a bending degree of a boundary line of the area picture relative to the straight line.
Acquiring the actual distortion degree of the regional picture, comparing the actual distortion degree with a preset distortion degree, when the actual distortion degree is greater than the preset distortion degree, performing distortion removal processing on the regional picture to obtain a distortion removed picture, specifically, obtaining the actual distortion degree of the regional picture by obtaining the bending degree of the boundary line of the regional picture relative to the straight line, further, judging whether the actual distortion degree is greater than the preset distortion degree, wherein the preset distortion degree is a quantity for measuring whether distortion affects the beauty of the picture, when the actual distortion degree is greater than the preset distortion degree, and carrying out distortion removal processing on the area picture to obtain a distortion removed picture, wherein when the actual distortion degree is less than or equal to the preset distortion degree, the distortion removal processing on the area picture is not required.
And step S25, adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized picture.
In this embodiment, the undistorted picture is adjusted through a preset picture optimization algorithm to obtain an optimized processed picture, where the preset picture optimization algorithm includes algorithms such as a sharpness adjustment algorithm and a light supplement algorithm, and specifically, the undistorted picture is optimized and adjusted through the preset picture optimization algorithm to optimize the undistorted picture, so that a visual effect of the undistorted picture is optimal, and the optimized processed picture is obtained.
Wherein the preset picture optimization algorithm comprises a preferred optimization algorithm and other optimization algorithms,
the step of adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized processed picture comprises the following steps:
step S251, obtaining an optimized optimization algorithm of the preset picture to be processed, and optimizing the undistorted picture based on the optimized optimization algorithm to obtain the undistorted picture;
in this embodiment, a preferred optimization algorithm of the preset to-be-processed picture is obtained, and the undistorted picture is optimized based on the preferred optimization algorithm to obtain the undistorted picture, specifically, the preferred optimization algorithm of the preset to-be-processed picture is obtained, where the optimization algorithm used when the preset to-be-processed picture is obtained is photographed in the preferred optimization algorithm, and then the undistorted picture is optimized based on the preferred optimization algorithm, so that the optimization effect of the preferred optimization algorithm is optimal, and the undistorted picture is obtained.
And step S252, acquiring a preset other optimization algorithm, and optimizing the distortion-removed picture again to obtain the optimized picture.
In this embodiment, a preset other optimization algorithm is obtained, the undistorted picture is optimized again, and the optimized processed picture is obtained, specifically, a preset other optimization algorithm other than the preferred optimization algorithm is obtained, the undistorted picture is optimized again, and the optimized processed picture is obtained, for example, if the optimal target is a human face, the preset other optimization algorithm, such as one of buffing, brightening, and dazzling, is called.
Wherein, the obtaining of the preset other optimization algorithm optimizes the undistorted picture again, and the obtaining of the optimized picture includes:
step A10, acquiring other preset optimization algorithms, and judging whether the optimal target is shielded;
in this embodiment, it should be noted that the preset other optimization algorithms include algorithms such as a deblocking algorithm and a target position adjustment algorithm, and the preset other optimization algorithms are preset and stored in a preset terminal database, and when the preset other optimization algorithms are required, the preset other optimization algorithms are called from the preset terminal database.
Obtaining a preset other optimization algorithm, and judging whether the optimal target is blocked, specifically, framing the optimal target to obtain a minimum rectangular target frame corresponding to the optimal target, wherein the minimum rectangular target frame is determined according to a boundary of the optimal target, that is, intersection points exist between four sides of the minimum rectangular target frame and the optimal target, further, if an intersection point exists between a blocking object and the optimal target, and the area ratio of the blocking object to the minimum rectangular target frame is greater than a preset threshold value, the optimal target is blocked, and if the blocking object does not have the intersection point with the optimal target or the area ratio of the blocking object to the minimum rectangular target frame is less than or equal to the preset threshold value, the optimal target is not blocked.
Step A20, when the optimal target is occluded, carrying out occlusion removing processing on the optimal target to obtain an occlusion removing picture;
in this embodiment, it should be noted that, before performing the picture optimization, the target standard feature corresponding to the optimal target is collected and stored in the preset feature database.
When the optimal target is shielded, performing shielding removal processing on the optimal target to obtain a shielding-removed picture, specifically, when the optimal target is shielded, extracting target features of the optimal target, matching target standard features corresponding to the target features in the preset feature database, and repairing the shielded optimal target based on the target standard features to obtain a complete optimal target image, that is, performing shielding removal processing on the optimal target to obtain a shielding-removed picture, and when the target is not shielded, directly performing target position optimization on the optimal target.
And A30, performing target position optimization on the occlusion-removed picture to obtain the optimized picture.
In this embodiment, it should be noted that, in a single picture, for the same object, the closer the object is to the lens, the larger the contour size of the object is, and the farther the object is from the lens, the smaller the contour size of the object is.
Optimizing the target position of the de-occlusion picture to obtain the optimized picture, specifically, adjusting the optimal target in the de-occlusion picture to the optimal position, wherein the optimal position comprises a position specified by a user, a picture center position, a position closest to the lens and the like, and further, according to the distance from the optimal target to the lens, adjusting the size of the optimal target to the size of the outline corresponding to the distance, namely, performing target position optimization on the de-occlusion picture to obtain the optimized processed picture, and in addition, in order to make the optimal target more prominent, the contour size of the optimal target can also be directly adjusted, for example, the optimal target is appropriately enlarged, and other targets are appropriately reduced, so that the optimal target is more prominent, after adjustment, the size of the optimal target has no corresponding relation with the distance from the optimal target to the lens.
This embodiment is through acquireing the target frame that optimal target corresponds, confirms the geometric center of target frame, and then based on geometric center, will the target frame carries out the magnification of predetermineeing the multiple, obtains enlarged target frame, through enlarged target frame is right optimal target is framed, obtains regional picture, further, obtains the actual distortion degree of regional picture, and will actual distortion degree compares with predetermineeing the distortion degree, works as actual distortion degree is greater than when predetermineeing the distortion degree, right regional picture carries out the distortion removal processing, obtains the distortion removal picture, and it is right through predetermineeing the picture optimization algorithm finally the distortion removal picture is adjusted, obtains the optimal processing picture. That is, in this embodiment, by obtaining the amplification target frame, the amplification target frame is used to frame the optimal target, so as to obtain the region picture, and then the region picture is subjected to the distortion removal processing, so as to obtain the distortion removal picture, and finally, the optimal processing picture is obtained by performing the optimal adjustment on the distortion removal picture. That is, the present embodiment implements optimization of the optimal target at any position in the image, and therefore, lays a foundation for solving the technical problem in the prior art that the optimal target of the image is poor in optimization effect when the image is photographed.
Further, referring to fig. 4, based on the first embodiment and the second embodiment in the present application, in another embodiment of the method for processing an image by optimizing an image, the step of obtaining a preset image to be processed and determining an optimal target in the preset image to be processed includes:
step B10, judging whether the optimal target is the face of the terminal user, and when the optimal target is the face of the terminal user, scanning the face of the terminal user through a preset face unlocking function to obtain the characteristics of the preset optimal target;
in this embodiment, it should be noted that, the picture optimization processing method is applied to a picture optimization processing device, the picture optimization processing device comprises a face unlocking function and is used for judging whether the optimal target is the face of an end user or not, when the optimal target is the face of the terminal user, scanning the face of the terminal user through a preset face unlocking function to obtain the preset optimal target characteristics, specifically, judging whether the optimal target is the face of the terminal user or not through user input information, wherein the user input information comprises information of target type, target name and the like, when the type and name of the optimal target are consistent with those of the face of the end user, the optimal target is judged to be the face of the end user, and then scanning the face of the terminal user through a preset face unlocking function to obtain the preset optimal target feature.
Step B20, when the optimal target is not the face of the end user, obtaining the related picture of the optimal target, and extracting a plurality of picture features in the related picture through a preset feature extractor;
in this embodiment, when the optimal target is not the face of the end user, a related picture of the optimal target is obtained, and a plurality of picture features in the related picture are extracted through a preset feature extractor, specifically, when the optimal target is not the face of the end user, the related picture of the optimal target is extracted from a local database of the terminal, and a plurality of picture features in the related picture are extracted through the preset feature extractor, where each picture feature includes a plurality of target features corresponding to targets in the related picture.
And step B30, classifying and screening the plurality of picture features to obtain the preset optimal target features.
In this embodiment, it should be noted that each of the image features includes a plurality of target features corresponding to targets in a related image, the plurality of image features are classified and screened to obtain the preset optimal target feature, specifically, the target features belonging to the same target in the plurality of image features are grouped into one group to obtain a plurality of target feature groups, further, the number of features in each target feature group is obtained, the target corresponding to the most number of features is an optimal target, and the target feature group corresponding to the optimal target is an optimal feature group, where the optimal target feature group includes a plurality of kinds of feature groups, for example, if the optimal target is a human face, the optimal target feature group includes an eye-type feature value, a nose-type feature value, a lip-type feature group value, and the like, and further, the optimal target feature set is screened, that is, a feature value range with the most dense feature value quantity distribution in various types of feature values is obtained as the preset optimal target feature, and then the preset optimal target feature is obtained, for example, if the optimal target is a human face, the eye type feature is an eye area proportion of glasses in the human face, wherein the eye area proportion of the optimal target is 5% to 6%, and in the eye type feature values, 90% of the feature value quantities are all distributed in 5.4% to 5.5% of the eye area proportion, so that the eye area proportions are all 5.4% to 5.5% as the preset optimal target feature.
The step of classifying and screening the plurality of picture features to obtain the preset optimal target feature comprises:
step B31, classifying the plurality of picture features to obtain a plurality of feature sets, wherein the same target in each related picture corresponds to one feature set;
in this embodiment, it should be noted that each of the related pictures includes a plurality of picture features, and then the picture features belonging to the same target are merged to obtain the feature set, where the feature set includes all picture feature values of one target.
Classifying the plurality of picture features to obtain a plurality of feature sets, specifically, grouping target features belonging to the same target in a plurality of target features in each picture feature to obtain a plurality of feature sets.
Step B32, acquiring the number of characteristic values in each characteristic set, and determining an optimal characteristic set based on the number of characteristic values;
in this embodiment, it should be noted that all the related pictures include the optimal target, so that the picture features corresponding to each related picture include feature values related to the optimal target, so that the number of feature values corresponding to the optimal target is the largest, and the number of the related pictures can ensure that the obtained optimal feature set is credible.
And acquiring the number of characteristic values in each characteristic set, determining an optimal characteristic set based on the number of the characteristic values, and specifically acquiring the number of characteristics of each target characteristic set, wherein the target corresponding to the most number of the characteristics is the optimal target, and the target characteristic set corresponding to the optimal target is the optimal characteristic set.
And step B33, analyzing the distribution condition of various characteristic values in the optimal characteristic set to obtain the preset optimal target characteristic.
In this embodiment, it should be noted that the optimal feature set includes multiple types of feature values, for example, if the optimal target corresponding to the optimal feature set is a human face, the multiple types of feature values include an eye type feature value, an eyebrow type feature value, a lip type feature value, and the like.
Analyzing the distribution conditions of various types of feature values in the optimal feature set to obtain the preset optimal target feature, specifically, obtaining feature value ranges of feature quantity distribution in various types of feature values, and grouping the feature value ranges to obtain a plurality of feature value range groups, and further obtaining a feature value range group with the most dense feature value quantity distribution, that is, obtaining the preset optimal target feature, for example, assuming that the optimal target is a human face, the eye type feature is the eye area proportion of glasses in the human face, and the eyebrow type feature is the eyebrow curvature, wherein the eye area proportion of the optimal target is 5% to 6%, and in the eye feature set, 90% of the feature value quantities are all the eye area proportion distributed in the feature value range of 5.4% to 5.5%, and the eyebrow curvature of the optimal target is 20 degrees to 30 degrees, and 96% of feature values in the eyebrow feature values are in the feature value range with the eyebrow bending degree of 22-23 degrees, so that the preset optimal target feature is obtained by setting the eye area ratio to be 5.4-5.5% and the eyebrow bending degree to be 22-23 degrees.
In this embodiment, it is first determined whether the optimal target is a face of an end user, when the optimal target is the face of the end user, the face of the end user is scanned through a preset face unlocking function to obtain preset optimal target features, when the optimal target is not the face of the end user, a related picture of the optimal target is obtained, a plurality of picture features in the related picture are extracted through a preset feature extractor, and then the plurality of picture features are classified and screened to obtain the preset optimal target features. That is, in this embodiment, first, whether the optimal target is the face of the end user is determined, when the optimal target is the face of the end user, preset optimal target features are obtained by scanning the face of the end user, when the optimal target is not the face of the end user, multiple picture features are obtained by extracting pictures related to the optimal target, and then the preset optimal target features are obtained by classifying and screening the multiple picture features. That is, the embodiment provides two ways to obtain the preset optimal target feature, and lays a foundation for determining the optimal target in the preset to-be-processed picture.
Referring to fig. 5, fig. 5 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 5, the picture optimization processing apparatus may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the picture optimization processing device may further include a target user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. The target user interface may comprise a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional target user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
It will be understood by those skilled in the art that the configuration of the picture optimization processing apparatus shown in fig. 5 does not constitute a limitation of the picture optimization processing apparatus, and may include more or less components than those shown, or combine some components, or arrange different components.
As shown in fig. 5, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, and a picture optimization processing program. The operating system is a program that manages and controls hardware and software resources of the picture optimization processing apparatus, and supports the operation of the picture optimization processing program and other software and/or programs. The network communication module is used for communication among the components in the memory 1005 and with other hardware and software in the picture optimization processing system.
In the apparatus for picture optimization processing shown in fig. 5, the processor 1001 is configured to execute a picture optimization processing program stored in the memory 1005, and implement the steps of the method for picture optimization processing described in any one of the above.
The specific implementation of the image optimization processing device of the present application is substantially the same as that of each embodiment of the image optimization processing method, and is not described herein again.
An embodiment of the present application further provides an image optimization processing apparatus, where the image optimization processing apparatus includes:
the present application further provides a picture optimization processing device, where the picture optimization processing device is applied to a picture optimization processing device, and the picture optimization processing device includes:
the determining module is used for acquiring a preset picture to be processed and determining an optimal target in the preset picture to be processed;
the optimization processing module is used for acquiring the area picture corresponding to the optimal target, and performing optimization processing on the area picture to acquire an optimized picture;
the fusion module is used for fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture;
and the output module is used for acquiring the target optimal picture group corresponding to the optimized picture, and arranging and outputting the pictures in the target optimal picture group.
Optionally, the optimization processing module includes:
the determining submodule is used for obtaining a target frame corresponding to the optimal target and determining a geometric center of the target frame;
the amplification sub-module is used for amplifying the target frame by a preset multiple based on the geometric center to obtain an amplified target frame;
the framing submodule is used for framing the optimal target through the amplified target frame to obtain a regional picture;
the distortion removing sub-module is used for acquiring the actual distortion degree of the regional picture, comparing the actual distortion degree with a preset distortion degree, and performing distortion removing processing on the regional picture to obtain a distortion removed picture when the actual distortion degree is greater than the preset distortion degree;
and the optimization submodule is used for adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized picture.
Optionally, the optimization submodule includes:
the optimization unit is used for acquiring the optimal optimization algorithm of the preset to-be-processed picture, and optimizing the undistorted picture based on the optimal optimization algorithm to obtain the undistorted picture;
and the re-optimization unit is used for acquiring and presetting other optimization algorithms, and performing re-optimization on the distortion-removed picture to acquire the optimized picture.
Optionally, the re-optimization unit comprises:
the first judgment subunit is used for acquiring the preset other optimization algorithms and judging whether the optimal target is blocked or not;
the shielding removing subunit is configured to, when the optimal target is shielded, perform shielding removing processing on the optimal target to obtain a shielding removed picture;
and the second judgment subunit is used for optimizing the target position of the occlusion-removed picture to obtain the optimized picture.
Optionally, the fusion module comprises:
a replacement sub-module, configured to replace a region range corresponding to the region picture in the optimized processed picture and the preset to-be-processed picture;
and the gradual change fusion submodule is used for performing gradual change fusion on the optimized picture and the preset picture to be processed, and adjusting the area which is not replaced in the preset picture to be processed based on the picture characteristics of the optimized picture to obtain the target optimal picture.
Optionally, the determining module includes:
the first feature extraction submodule is used for acquiring a preset to-be-processed picture, and performing feature extraction on a candidate target in the preset to-be-processed picture to acquire a candidate target feature;
and the comparison submodule is used for comparing each candidate target characteristic with a preset optimal target characteristic and determining an optimal target in the preset to-be-processed picture.
Optionally, the picture optimization processing apparatus further includes:
the second feature extraction module is used for judging whether the optimal target is the face of the terminal user or not, and when the optimal target is the face of the terminal user, scanning the face of the terminal user through a preset face unlocking function to obtain the preset optimal target feature;
the third feature extraction module is used for acquiring a related picture of the optimal target when the optimal target is not the face of an end user, and extracting a plurality of picture features in the related picture through a preset feature extractor;
and the classification screening module is used for classifying and screening the plurality of picture features to obtain the preset optimal target feature.
Optionally, the classification screening module includes:
the classification submodule is used for classifying the plurality of picture features to obtain a plurality of feature sets, wherein the same target in each related picture corresponds to one feature set;
the screening submodule is used for acquiring the quantity of characteristic values in each characteristic set and determining an optimal characteristic set based on the quantity of the characteristic values;
and the analysis and determination submodule is used for analyzing the distribution condition of various characteristic values in the optimal characteristic set to obtain the preset optimal target characteristic.
The specific implementation of the image optimization processing apparatus of the present application is substantially the same as that of each of the embodiments of the image optimization processing method, and is not described herein again.
The present application provides a readable storage medium, where one or more programs are stored, and the one or more programs are further executable by one or more processors for implementing the steps of the picture optimization processing method described in any one of the above.
The specific implementation of the readable storage medium of the present application is substantially the same as the embodiments of the image optimization processing method, and is not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (11)
1. An image optimization processing method, characterized in that the image optimization processing method comprises:
acquiring a preset picture to be processed, and determining an optimal target in the preset picture to be processed;
obtaining a region picture corresponding to the optimal target, and optimizing the region picture to obtain an optimized picture;
and fusing the optimized picture and the preset picture to be processed to obtain a target optimal picture.
2. The method according to claim 1, wherein the step of obtaining the region picture corresponding to the optimal target and performing optimization processing on the region picture to obtain the optimized processed picture comprises:
acquiring a target frame corresponding to the optimal target, and determining the geometric center of the target frame;
based on the geometric center, amplifying the target frame by a preset multiple to obtain an amplified target frame;
framing the optimal target through the amplified target frame to obtain a regional picture;
acquiring the actual distortion degree of the regional picture, comparing the actual distortion degree with a preset distortion degree, and when the actual distortion degree is greater than the preset distortion degree, performing distortion removal processing on the regional picture to obtain a distortion removed picture;
and adjusting the undistorted picture by a preset picture optimization algorithm to obtain an optimized picture.
3. The picture optimization processing method according to claim 2, wherein the preset picture optimization algorithm comprises a preferred optimization algorithm and other optimization algorithms,
the step of adjusting the undistorted picture through a preset picture optimization algorithm to obtain an optimized processed picture comprises the following steps:
acquiring an optimal optimization algorithm of the preset picture to be processed, and optimizing the undistorted picture based on the optimal optimization algorithm to obtain the undistorted picture;
and acquiring other preset optimization algorithms, and optimizing the distortion-removed picture again to obtain the optimized picture.
4. The method as claimed in claim 3, wherein said obtaining of the predetermined other optimization algorithm optimizes the undistorted picture again, and the step of obtaining the optimized picture comprises:
acquiring other preset optimization algorithms, and judging whether the optimal target is shielded or not;
when the optimal target is shielded, carrying out shielding removal processing on the optimal target to obtain a shielding removal picture;
and optimizing the target position of the occlusion-removed picture to obtain the optimized picture.
5. The method according to claim 1, wherein the step of fusing the optimized picture with the preset picture to be processed to obtain a target optimal picture comprises:
replacing the area range corresponding to the area picture in the optimized picture and the preset picture to be processed;
and performing gradual fusion on the optimized picture and the preset picture to be processed, and adjusting an area which is not replaced in the preset picture to be processed based on the picture characteristics of the optimized picture to obtain a target optimal picture.
6. The method as claimed in claim 1, wherein the step of obtaining a preset to-be-processed picture and determining an optimal target in the preset to-be-processed picture comprises:
acquiring a preset picture to be processed, and extracting the characteristics of a candidate target in the preset picture to be processed to obtain the characteristics of the candidate target;
and comparing each candidate target characteristic with a preset optimal target characteristic to determine an optimal target in the preset to-be-processed picture.
7. The method according to claim 6, wherein the step of obtaining the preset to-be-processed picture and determining the optimal target in the preset to-be-processed picture comprises:
judging whether the optimal target is the face of an end user, and when the optimal target is the face of the end user, scanning the face of the end user through a preset face unlocking function to obtain the preset optimal target feature;
when the optimal target is not the face of an end user, acquiring a related picture of the optimal target, and extracting a plurality of picture features in the related picture through a preset feature extractor;
and classifying and screening the plurality of picture features to obtain the preset optimal target feature.
8. The method according to claim 7, wherein the step of classifying and screening the plurality of picture features to obtain the preset optimal target feature comprises:
classifying the plurality of picture features to obtain a plurality of feature sets, wherein the same target in each related picture corresponds to one feature set;
acquiring the quantity of characteristic values in each characteristic set, and determining an optimal characteristic set based on the quantity of the characteristic values;
and analyzing the distribution condition of various characteristic values in the optimal characteristic set to obtain the preset optimal target characteristic.
9. The picture optimization processing device is applied to a picture optimization processing device, and comprises:
the determining module is used for acquiring a preset picture to be processed and determining an optimal target in the preset picture to be processed;
the optimization processing module is used for acquiring the area picture corresponding to the optimal target, and performing optimization processing on the area picture to acquire an optimized picture;
and the output module is used for acquiring the target optimal picture group corresponding to the optimized picture, and arranging and outputting the pictures in the target optimal picture group.
10. A picture optimization processing apparatus, characterized by comprising: a memory, a processor, and a program stored on the memory for implementing the picture optimization processing method,
the memory is used for storing a program for realizing the picture optimization processing method;
the processor is configured to execute a program for implementing the picture optimization processing method to implement the steps of the picture optimization processing method according to any one of claims 1 to 8.
11. A readable storage medium having a program for implementing a picture optimization processing method stored thereon, the program being executed by a processor to implement the steps of the picture optimization processing method according to any one of claims 1 to 8.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911297408.9A CN111080553A (en) | 2019-12-13 | 2019-12-13 | Picture optimization processing method, device and equipment and readable storage medium |
| PCT/CN2020/081457 WO2021114510A1 (en) | 2019-12-13 | 2020-03-26 | Picture optimization processing method, apparatus and device, and readable storage medium |
| CN202080086940.0A CN114930382A (en) | 2019-12-13 | 2020-03-26 | Picture optimization processing method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911297408.9A CN111080553A (en) | 2019-12-13 | 2019-12-13 | Picture optimization processing method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080553A true CN111080553A (en) | 2020-04-28 |
Family
ID=70314888
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911297408.9A Pending CN111080553A (en) | 2019-12-13 | 2019-12-13 | Picture optimization processing method, device and equipment and readable storage medium |
| CN202080086940.0A Pending CN114930382A (en) | 2019-12-13 | 2020-03-26 | Picture optimization processing method, device and equipment and readable storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080086940.0A Pending CN114930382A (en) | 2019-12-13 | 2020-03-26 | Picture optimization processing method, device and equipment and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (2) | CN111080553A (en) |
| WO (1) | WO2021114510A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612713A (en) * | 2020-05-19 | 2020-09-01 | 深圳度影医疗科技有限公司 | Shielding removing method of three-dimensional ultrasonic image |
| CN111814763A (en) * | 2020-08-26 | 2020-10-23 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN115396717A (en) * | 2022-08-23 | 2022-11-25 | 海信视像科技股份有限公司 | Display device and display image quality adjusting method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101385599B1 (en) * | 2012-09-26 | 2014-04-16 | 한국과학기술연구원 | Method and apparatus for interfering montage |
| KR102370063B1 (en) * | 2017-03-28 | 2022-03-04 | 삼성전자주식회사 | Method and apparatus for verifying face |
| CN110213476A (en) * | 2018-02-28 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Image processing method and device |
-
2019
- 2019-12-13 CN CN201911297408.9A patent/CN111080553A/en active Pending
-
2020
- 2020-03-26 CN CN202080086940.0A patent/CN114930382A/en active Pending
- 2020-03-26 WO PCT/CN2020/081457 patent/WO2021114510A1/en active Application Filing
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612713A (en) * | 2020-05-19 | 2020-09-01 | 深圳度影医疗科技有限公司 | Shielding removing method of three-dimensional ultrasonic image |
| CN111612713B (en) * | 2020-05-19 | 2023-11-03 | 深圳度影医疗科技有限公司 | Method for removing occlusion of three-dimensional ultrasonic image |
| CN111814763A (en) * | 2020-08-26 | 2020-10-23 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN111814763B (en) * | 2020-08-26 | 2021-01-08 | 长沙鹏阳信息技术有限公司 | Noninductive attendance and uniform identification method based on tracking sequence |
| CN115396717A (en) * | 2022-08-23 | 2022-11-25 | 海信视像科技股份有限公司 | Display device and display image quality adjusting method |
| CN115396717B (en) * | 2022-08-23 | 2024-05-17 | 海信视像科技股份有限公司 | Display device and display image quality adjusting method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021114510A1 (en) | 2021-06-17 |
| CN114930382A (en) | 2022-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111885294B (en) | Shooting method, device and equipment | |
| WO2019105154A1 (en) | Image processing method, apparatus and device | |
| US7912363B2 (en) | Object determining device and imaging apparatus | |
| CN111080553A (en) | Picture optimization processing method, device and equipment and readable storage medium | |
| US20170228867A1 (en) | Method and system of image segmentation refinement for image processing | |
| WO2018223394A1 (en) | Method and apparatus for photographing image | |
| CN115052104B (en) | Image processing method, electronic device, and non-volatile computer-readable storage medium | |
| CN113837079B (en) | Automatic focusing method, device, computer equipment and storage medium of microscope | |
| CN110650288B (en) | Focusing control method and device, electronic equipment and computer readable storage medium | |
| CN110855957B (en) | Image processing method and device, storage medium and electronic equipment | |
| CN111242074B (en) | Certificate photo background replacement method based on image processing | |
| CN113965664B (en) | Image blurring method, storage medium and terminal equipment | |
| JP2009027702A (en) | Method for calibrating camera for acquiring first frame in multi-frame source image, and system for acquiring photographs of multiple frames in multi-frame source image | |
| CN111050027A (en) | Lens distortion compensation method, device, equipment and storage medium | |
| CN113938578B (en) | Image blurring method, storage medium and terminal equipment | |
| US10373329B2 (en) | Information processing apparatus, information processing method and storage medium for determining an image to be subjected to a character recognition processing | |
| CN111630569B (en) | Binocular matching method, visual imaging device and device with storage function | |
| WO2023060756A1 (en) | Face anti-spoofing detection method and device, and readable storage medium and computer program product | |
| CN113724129B (en) | Image blurring method, storage medium and terminal equipment | |
| CN113395434B (en) | Preview image blurring method, storage medium and terminal equipment | |
| KR20150032764A (en) | Method and image capturing device for generating artificially defocused blurred image | |
| CN111862098B (en) | Individual matching method, device, equipment and medium based on light field semantics | |
| CN112188075B (en) | Snapshot, image processing device and image processing method | |
| JP2018136789A (en) | Image processing device, image processing method and image processing program | |
| JP5582924B2 (en) | Image processing apparatus, image processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221226 Address after: 201203 1st floor, building 1, Lane 36, Xuelin Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 201203 Applicant after: SHANGHAI TRANSSION INFORMATION TECHNOLOGY Ltd. Address before: Room 922 / 926, block a, No. 1, Lane 399, shengxia Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 201203 Applicant before: SHANGHAI SPREADRISE COMMUNICATION TECHNOLOGY Ltd. |
|
| TA01 | Transfer of patent application right |