CN107659806B - The appraisal procedure and device of video quality - Google Patents
The appraisal procedure and device of video quality Download PDFInfo
- Publication number
- CN107659806B CN107659806B CN201710725869.6A CN201710725869A CN107659806B CN 107659806 B CN107659806 B CN 107659806B CN 201710725869 A CN201710725869 A CN 201710725869A CN 107659806 B CN107659806 B CN 107659806B
- Authority
- CN
- China
- Prior art keywords
- quality
- reference picture
- distorted image
- mass
- evaluating
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 248
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 37
- 238000010801 machine learning Methods 0.000 claims description 18
- 238000013441 quality evaluation Methods 0.000 claims description 14
- 239000012141 concentrate Substances 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 15
- 238000011156 evaluation Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 230000000903 blocking effect Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 238000003646 Spearman's rank correlation coefficient Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000013021 vision distortion Diseases 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Analysis (AREA)
Abstract
The application provides the appraisal procedure and device of a kind of video quality, this method comprises: obtaining training dataset, it includes at least one source images and at least one distorted image corresponding with each source images that the training data, which is concentrated,；Calculate the first mass of each source images；Calculate second mass of at least one described distorted image relative to the source images；According to first mass and second mass, the quality of image is determined.The accuracy of video quality assessment can be improved in the appraisal procedure and device of video quality provided by the present application.
Description
Technical field
The invention relates to image and video quality evaluation field more particularly to a kind of appraisal procedures of video quality
And device.
Background technique
With the development of the communication technology and multimedia technology, video is widely developed and applies, application scenarios
It more complicates, therefore, how the quality of video is accurately assessed, be an extremely important problem.
Fig. 1 is the flow diagram assessed in the prior art video quality, as shown in Figure 1, dividing video into
After multiple image, by benchmark image by encoder encode after obtain assessment object, and assume assessment object include blocking artifact and
Two kinds of type of distortion are obscured, benchmark image and assessment object are had into reference picture method for evaluating quality (method 1 by multiple respectively
With method 2) it is assessed, wherein method 1 and method 2 for example can be visual information fidelity (Visual Information
Fidelity；) and loss in detail index (Detail Loss Metric VIF；DLM) etc., there is reference picture quality by multiple
After appraisal procedure carries out quality evaluation, then multiple results of acquisition are weighted processing by machine learning, to obtain the figure
The quality score of picture.
However, in the prior art have reference picture method for evaluating quality, due to being assuming that the benchmark image chosen is
It is carried out under the premise of perfect quality, so as to cause the assessment result inaccuracy of video quality.
Summary of the invention
The embodiment of the present application provides the appraisal procedure and device of a kind of video quality, to solve the assessment result of video quality
The technical problem of inaccuracy.
The application first aspect provides a kind of appraisal procedure of video quality, comprising:
Training dataset is obtained, it includes at least one source images and corresponding with each source images that the training data, which is concentrated,
At least one distorted image；
Calculate the first mass of each source images；
Calculate second mass of at least one described distorted image relative to the source images；
According to first mass and second mass, the quality of image is determined.
In the present solution, source images are high quality graphic, server can pass through non-reference picture method for evaluating quality meter
The first mass of each source images is calculated, and by there is reference picture method for evaluating quality to calculate the corresponding each distortion of each source images
Second mass of image finally combines calculated first mass and the second mass, can determine the image for needing to assess
Quality.
It in the above scheme, include at least one source images and at least one distortion corresponding with each source images by obtaining
The training dataset of image, and the first mass for calculating each source images and at least one distorted image are relative to source images
Second mass determines the quality of image further according to the first mass and the second mass.Due to the first matter by calculating source images
Amount, and the quality for needing the image assessed is determined according to calculated first mass and the second mass, so as to avoid existing skill
The phenomenon that carrying out quality evaluation under the premise of assuming that the benchmark image chosen is perfect is needed in art, it is possible thereby to improve video
The accuracy of quality evaluation.
In one implementation, second matter for calculating at least one described distorted image relative to the source images
Amount, comprising:
Determine the type of distortion and distortion level of each distorted image；
According to the type of distortion and the distortion level, each distorted image is grouped, obtains at least one distortion
Image group, wherein the type of distortion and distortion level of the distorted image in same distorted image group are all the same；
According to multiple first assessment results and the second assessment result, has in reference picture method for evaluating quality from m and determine
N therein have reference picture method for evaluating quality；First assessment result is to be respectively adopted the m to have reference picture matter
Appraisal procedure is measured, it is being obtained after assessing the distorted image in each distorted image group as a result, the second assessment knot
Fruit is to be obtained after user's subjectivity assesses each distorted image as a result, m and n are positive integer, and m is greater than or equal to n；
There is reference picture method for evaluating quality according to the n, calculates second mass.
In one implementation, described according to multiple first assessment results and the second assessment result, have from m with reference to figure
As determining n method therein in method for evaluating quality, comprising:
There is reference picture method for evaluating quality by m, the distorted image in each distorted image group is carried out respectively
Assessment obtains multiple first assessment results；
In each distorted image group, according to multiple first assessment results, there is reference picture quality to comment from the m
Estimate and determines that t therein has reference picture method for evaluating quality in method；The t have reference picture method for evaluating quality be by
Have according to m consistent between corresponding first assessment result of reference picture method for evaluating quality and second assessment result
The sequence of property degree from high to low, the preceding t degree of consistency selected is corresponding reference picture method for evaluating quality；
Have in reference picture method for evaluating quality according to corresponding the t of all distorted image groups and each have reference
The sequence of the frequency that image quality measure method occurs from high to low, n have reference picture method for evaluating quality before determining；Its
In, t is the positive integer less than or equal to m, and more than or equal to n.
In the present solution, type of distortion for example may include obscure, blocking artifact, color are abnormal, flower screen and contrast are abnormal
It for example may include slight, moderate and severe etc. Deng, distortion level, can be indicated with discrete range format.In addition,
The reference picture method for evaluating quality that has of existing prevalence may include Y-PSNR (Peak Signal to Noise
Ratio；PSNR), structural similarity (Structural SIMilarity；SSIM), Multi-scale model similitude (Multi-
Scale SSIM；MS-SSIM), visual information fidelity (Visual Information Fidelity；VIF), loss in detail
Index (Detail Loss Metric；) and characteristic similarity (Feature SIMilarity DLM；FSIM) etc..
In one implementation, described to have reference picture method for evaluating quality according to the n, calculate second matter
Amount, comprising:
The quality for having reference picture method for evaluating quality to calculate the distorted image by n respectively, obtains multiple thirds
Quality；
The multiple third quality is weighted processing by machine learning, obtains second mass.
In the present solution, server after determining that n have reference picture method for evaluating quality, has passing through n respectively
Reference picture method for evaluating quality calculates the quality of each distorted image, obtains multiple third quality, and pass through machine learning side
Multiple third quality are weighted processing by method, to obtain the second mass.Wherein, machine learning method may include support to
Amount returns (Support Vector Machine；) and support vector regression (Support Vector Regression SVM；
SVR) etc..
It is weighted processing about by machine learning, the result obtained using a variety of machine learning methods and user are subjective
The result of evaluation compares, and obtains optimal performance appraisal procedure according to Performance Evaluation index (PCC, SROCC, RMSE), thus
The accuracy of the second Mass Calculation can be improved.Wherein, Performance Evaluation index includes Pearson came linearly dependent coefficient (Pearson
Linear Correlation Efficient；PLCC), Spearman rank correlation coefficient (Spearman's Rank
Correlation Coefficient；) and root-mean-square error (Root Mean Square Error SROCC；RMSE) etc..
In one implementation, first mass for calculating each source images, comprising:
According to the pixel domain of each source images, first mass is calculated.
In one implementation, described that the quality of image is determined according to first mass and second mass, packet
It includes:
First mass is subjected to standardization processing, obtains quality coefficient, the value of the quality coefficient is greater than or equal to
0.0, and it is less than or equal to 1.0；
By the quality coefficient multiplied by second mass, and the result of acquisition is determined as to the quality of described image.
The application second aspect provides a kind of assessment device of video quality, comprising:
Acquiring unit, for obtaining training dataset, the training data concentrate include at least one source images and with it is each
At least one corresponding distorted image of the source images；
Computing unit, for calculating the first mass of each source images；
The computing unit is also used to calculate second matter of at least one described distorted image relative to the source images
Amount；
Determination unit, for determining the quality of image according to first mass and second mass.
In one implementation, the computing unit, comprising:
Subelement is determined, for determining the type of distortion and distortion level of each distorted image；
It is grouped subelement, for being grouped, obtaining to each distorted image according to the type of distortion and the distortion level
Obtain at least one distorted image group, wherein the type of distortion and distortion level of the distorted image in same distorted image group
It is all the same；
The determining subelement is also used to be had from m with reference to figure according to multiple first assessment results and the second assessment result
As determining that n therein has reference picture method for evaluating quality in method for evaluating quality；First assessment result is to adopt respectively
There is reference picture method for evaluating quality with the m, is obtained after assessing the distorted image in each distorted image group
As a result, second assessment result is to be obtained after user's subjectivity assesses each distorted image as a result, m and n are
Positive integer, and m is greater than or equal to n；
Computation subunit calculates second mass for having reference picture method for evaluating quality according to the n.
In one implementation, the determining subelement, is specifically used for:
There is reference picture method for evaluating quality by m, the distorted image in each distorted image group is carried out respectively
Assessment obtains multiple first assessment results；
In each distorted image group, according to multiple first assessment results, there is reference picture quality to comment from the m
Estimate and determines that t therein has reference picture method for evaluating quality in method；The t have reference picture method for evaluating quality be by
Have according to m consistent between corresponding first assessment result of reference picture method for evaluating quality and second assessment result
The sequence of property degree from high to low, the preceding t similarity selected is corresponding reference picture method for evaluating quality；
Have in reference picture method for evaluating quality according to corresponding the t of all distorted image groups and each have reference
The sequence of the frequency that image quality measure method occurs from high to low, n have reference picture method for evaluating quality before determining；Its
In, t is the positive integer less than or equal to m, and more than or equal to n.
In one implementation, the computation subunit, is specifically used for:
The quality for having reference picture method for evaluating quality to calculate the distorted image by n respectively, obtains multiple thirds
Quality；
The multiple third quality is weighted processing by machine learning, obtains second mass.
In one implementation, the computing unit, is specifically used for:
According to the pixel domain of each source images, first mass is calculated.
In one implementation, the determination unit is specifically used for:
First mass is subjected to standardization processing, obtains quality coefficient, the value of the quality coefficient is greater than or equal to
0.0, and it is less than or equal to 1.0；
By the quality coefficient multiplied by second mass, and the result of acquisition is determined as to the quality of described image.
The application third aspect provides a kind of assessment device of video quality, which includes processor and memory, deposits
Reservoir calls the program of memory storage for storing program, processor, the method to execute the offer of the application first aspect.
The application fourth aspect provides a kind of server, including at least one of the method for executing the above first aspect
Processing element (or chip).
The 5th aspect of the application provides a kind of appraisal procedure of video quality, and the program is when being executed by processor for holding
The method of the above first aspect of row.
The 6th aspect of the application provides a kind of program product, such as computer readable storage medium, including the 5th aspect
Program.
The appraisal procedure and device of video quality provided by the present application, by obtain include at least one source images and with it is each
The training dataset of at least one corresponding distorted image of source images, and the first mass of each source images is calculated, and at least one
Second mass of a distorted image relative to source images determines the quality of image further according to the first mass and the second mass.Due to
The image for needing to assess is determined by calculating the first mass of source images, and according to calculated first mass and the second mass
Quality, so as to avoid needing to carry out quality evaluation under the premise of assuming that the benchmark image chosen is perfect in the prior art
Phenomenon, it is possible thereby to improve the accuracy of video quality assessment.
Detailed description of the invention
Fig. 1 is the flow diagram assessed in the prior art video quality；
Fig. 2 is the usage scenario schematic diagram of the appraisal procedure of video quality provided by the embodiments of the present application；
Fig. 3 is the flow diagram of the appraisal procedure embodiment one of video quality provided by the embodiments of the present application；
Fig. 4 is the flow diagram for calculating the second mass；
Fig. 5 is the structural schematic diagram of the assessment Installation practice one of video quality provided by the embodiments of the present application；
Fig. 6 is the structural schematic diagram of the assessment Installation practice two of video quality provided by the embodiments of the present application；
Fig. 7 A is a kind of possible structural schematic diagram of the application server；
Fig. 7 B is the alternatively possible structural schematic diagram of the application server.
Specific embodiment
The appraisal procedure of video quality provided by the embodiments of the present application can be adapted for volume/transcoded quality assessment scene
In, Fig. 2 is the usage scenario schematic diagram of the appraisal procedure of video quality provided by the embodiments of the present application, as shown in Fig. 2, video takes
The process of business is as follows: (1) being initially injected video source contents, i.e. film source；(2) film source is switched to by various code rate by volume/transcoder
Version, various code rate version corresponds to different quality, in this process, in order to guarantee volume/transcoder output stream quality
Meet predeterminated target requirement, it is therefore desirable to assess coding source quality, and then cataloged procedure is carried out according to assessment result and is determined
Plan, such as coding output quality and aimed quality setting will reset coding parameter when not being inconsistent and implement new cataloged procedure, in this way,
It can be very good the experience of guarantee user；(3) it is packaged, encapsulated and sent out for meeting the encoded output stream of predeterminated target requirement
Stream；(4) video flowing carries out network transmission；(5) user watches Video service by terminal device.Therefore it provides a kind of accuracy
The appraisal procedure of higher video quality, for guaranteeing that the experience of user is very important.
The appraisal procedure of video quality provided by the present application, it is intended to which the appraisal procedure for solving video quality in the prior art is commented
The technical problem for the result inaccuracy estimated.
How the technical solution of the application and the technical solution of the application are solved with specifically embodiment below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, embodiments herein is described.
Fig. 3 is the flow diagram of the appraisal procedure embodiment one of video quality provided by the embodiments of the present application.The application
The appraisal procedure for the video quality that embodiment provides can be executed by the device for arbitrarily executing the appraisal procedure of video quality, should
Device can pass through software and or hardware realization.In the present embodiment, which be can integrate in the server.As shown in figure 3,
The method of the present embodiment may include:
Step 301, obtain training dataset, the training data concentrate include at least one source images and with each source images pair
At least one distorted image answered.
In the present embodiment, training data concentrate include at least one source images and it is corresponding with each source images at least one
Distorted image, wherein source images are at least frame image in video to be assessed, which is high quality and undistorted
Image.For each source images, after passing it through encoder coding, it will at least one corresponding distorted image is obtained,
At least one distorted image corresponding from each source images usually requires to be related to the mistake of different type of distortion and different levels
True degree.Wherein, type of distortion for example may include obscuring, blocking artifact, color exception, spending screen and contrast exception etc., distortion
Degree for example may include slight, moderate and severe etc., can be indicated with discrete range format, such as the mistake of image
When true degree is between 0-30%, distortion level be it is slight, when the distortion factor is between 31%-70%, distortion level is moderate, is distorted
When degree is between 71%-100%, distortion level is severe etc., above distortion level by way of example only, in concrete implementation
In the process, the grade of distortion level and can according to the actual situation or experience is configured to the specific division of each grade,
Grade for distortion level and the specific division mode to each grade, this is not restricted for the present embodiment.
Step 302, the first mass for calculating each source images.
In the present embodiment, server will calculate the first mass of each source images after getting training dataset,
That is the proper mass of source images.In a kind of possible embodiment, server will pass through non-reference picture method for evaluating quality
Calculate the first mass of each source images.The first mass is calculated herein according to the pixel domain of each source images.Specifically, no reference
Image quality measure method when assessing image/video quality, does not compare benchmark, directly according to the feature of object to be assessed
Or quality score is calculated in parameter.The quality of pixel domain is to assess the essential proper mass of object, and the quality of compression domain is then
It is mass change caused by the compression process of assessment, on the input of encoder, there is no premised on vision distortion problem.
Step 303 calculates second mass of at least one distorted image relative to source images.
In the present embodiment, server is after getting training dataset, will calculate each source images it is corresponding at least one
Second mass of distorted image, i.e. quality of the distorted image relative to source images.In one embodiment, server will pass through
There is reference picture method for evaluating quality to calculate the second mass of at least one distorted image, further, server passes through mixing
Type has reference picture method for evaluating quality to calculate the second mass.
Fig. 4 is the flow diagram for calculating the second mass, as shown in figure 4, the calculation specifically includes:
Step 3031, the type of distortion and distortion level for determining each distorted image.
Specifically, the corresponding distorted image of each of training dataset source images may all correspond to a variety of distortion classes
Type, each type of distortion may correspond to a variety of distortion levels, and therefore, for each distorted image, server will be determined and be lost
The type of distortion and distortion level of true image, wherein type of distortion may include obscure, blocking artifact, color are abnormal, flower screen and right
More abnormal etc. than degree, distortion level can be determined according to the distortion factor of image.Such as: the corresponding distorted image of source images 1 is image
11, image 12, image 13, image 14 and image 15, the type of distortion of image 11 be it is fuzzy, distortion level is slight, image 12
Type of distortion be it is fuzzy, distortion level is severe, and the type of distortion of image 13 is blocking artifact, and distortion level is moderate, image
14 type of distortion is that color is abnormal, and distortion level is moderate, and the type of distortion of image 15 is that color is abnormal, and distortion level is light
Degree.
It needs to be illustrated, is calculated in step 302 and determine type of distortion and distortion in first mass and step 3031
It is decoupling between the process of degree, wherein calculate the first mass in step 302 and can be and be distorted independent of in step 3031
Detection, be also possible to dependence formula, but have differences therebetween: independent of the mode of distortion detection, to video quality
Assessment result accuracy be higher than the mode relied on, and be suitable for weak distortion scene, herein for source nothing participate in evaluation and electing point use it is non-
Dependence formula.
Step 3032, according to type of distortion and distortion level, each distorted image is grouped, at least one distortion is obtained
Image group, wherein the type of distortion of the distorted image in same distorted image group and distortion level section are all the same.
Specifically, server is after the type of distortion and distortion level for determining each distorted image, will be according to determining
Type of distortion and distortion level distorted image is grouped, can be by type of distortion and mistake during concrete implementation
True degree distorted image all the same is divided into one group.Table 1 show to each distorted image be grouped as a result, as shown in table 1,
Type of distortion can indicate that distortion level can be indicated with 1,2,3 ... M with a, b, c ....
Table 1
Step 3033, according to multiple first assessment results and the second assessment result, have reference picture quality evaluation side from m
N are determined in method reference picture method for evaluating quality；First assessment result is to be respectively adopted m to have reference picture quality to comment
Estimate method, it is being obtained after assessing the distorted image in each distorted image group as a result, second assessment result is to use householder
See each distorted image is assessed after obtain as a result, m and n be positive integer, and m be greater than or equal to n.
Specifically, the mode for carrying out quality evaluation to image/video generally includes two classes, respectively subjective evaluation method and
Objective evaluation method, wherein subjective evaluation method be user in specific controlled environment (including viewing distance, viewing duration,
Illumination, the selection of test object, personnel's selection etc.) test video is beaten by subjective feeling according to the opinion scale of regulation
Point, all evaluation score values are weighted and averaged to obtain Mean Opinion Score (Mean Opinion Score；MOS) value, i.e., it is subjective
Scoring.Subjective method can accurately reflect the quality of image/video, be true user experience.But this method implement it is cumbersome,
Real-time is poor and can not automate, and is unfavorable for the system integration and realization, it is impossible to be used in actual business.Objective method is a kind of standard
It is true, being easily achieved, the appraisal procedure used can be automated, accuracy passes through the consistency journey with subjective method result
Degree is measured.Its realization is the feature or parameter according to evaluation object, passes through and calculates acquisition quality score.Objective method is according to ginseng
The use for examining source information (i.e. assessment benchmark), which is divided into, to be had with reference to and without with reference to two classes.There is reference (reference) method: assessing
When the quality of image/video object, there are the benchmark of comparison, i.e. reference source, by the feature for differentiating object and reference source to be assessed
Or the difference or variation of parameter, obtain assessment result.
It can use above-mentioned subjective evaluation method in the present embodiment and utilize objective evaluation method, have from m with reference to figure
As determining that n have reference picture method for evaluating quality in method for evaluating quality, wherein the first assessment result is to be respectively adopted m
There is reference picture method for evaluating quality, it is being obtained after assessing the distorted image in each distorted image group as a result, utilizing
It is that above-mentioned objective evaluation method obtains as a result, the second assessment result is to obtain after user's subjectivity assesses each distorted image
As a result, the result obtained using above-mentioned subjective evaluation method.
The n processes for having reference picture method for evaluating quality how are determined in the following, will be described in detail.
Server passes through m first reference picture method for evaluating quality, respectively to the distortion map in each distorted image group
As being assessed, multiple first assessment results are obtained；In each distorted image group, according to multiple first assessment results, from m
Have and determine that t have reference picture method for evaluating quality in reference picture method for evaluating quality, wherein t have reference picture quality
Appraisal procedure is to have between corresponding first assessment result of reference picture method for evaluating quality and the second assessment result according to m
The sequence of the degree of consistency from high to low, the preceding t degree of consistency selected is corresponding reference picture method for evaluating quality；
Being had according to all distorted image groups corresponding t each has reference picture method for evaluating quality in reference picture method for evaluating quality
The sequence of the frequency of appearance from high to low, n has reference picture method for evaluating quality before determining, wherein t be less than or equal to
M, and it is greater than or equal to the positive integer of n.
Specifically, the reference picture method for evaluating quality that has of existing prevalence may include Y-PSNR (Peak Signal
to Noise Ratio；PSNR), structural similarity (Structural SIMilarity；SSIM), Multi-scale model similitude
(Multi-Scale SSIM；MS-SSIM), visual information fidelity (Visual Information Fidelity；VIF), thin
Section loses index (Detail Loss Metric；) and characteristic similarity (Feature SIMilarity DLM；FSIM) etc., when
So, in addition to above-mentioned appraisal procedure, having reference picture method for evaluating quality can also include other methods, for specifically there is ginseng
Examine image quality measure method, can be selected according to the actual situation, the present embodiment to this with no restriction.
Server by m it is different have reference picture method for evaluating quality, respectively to the mistake in each distorted image group
True image is assessed, such as: in the distorted image group that type of distortion is a and distortion level is 1 include image 11, image 12,
Image 13 and image 14 respectively can then assess image 11, image 12, image 13 and image 14 by PSNR method,
The first assessment result is obtained, image 11, image 12, image 13 and image 14 are assessed respectively by SSIM method, is obtained
First assessment result respectively assesses image 11, image 12, image 13 and image 14 by MS-SSIM method, obtains the
One assessment result respectively assesses image 11, image 12, image 13 and image 14 by VIF method, obtains the first assessment
As a result etc., similarly, each distorted image in other distorted image groups is also similarly evaluated, it is possible thereby to obtain multiple
One assessment result.
For each distorted image group, after obtaining multiple first assessment results, can according to the first assessment result and
The sequence of the degree of consistency from high to low between second assessment result, the t degree of consistency is corresponding before selecting reference
Image quality measure method.As an example it is assumed that m is 4, t 3, the distorted image group that type of distortion is a and distortion level is 1
In include image 11, image 12, image 13 and image 14, what user's subjectivity obtained after assessing each distorted image second comments
The score value for estimating result is 80,90,85 and 82, and server is by PSNR method respectively to image 11, image 12, image 13 and image
14 are assessed, and the score value of the first assessment result of acquisition is 80,88,83 and 82, the first assessment result and the second assessment result
Between the degree of consistency be 95%, server by SSIM method respectively to image 11, image 12, image 13 and image 14 into
Row assessment, the score value for obtaining the first assessment result is 75,93,82 and 80, between the first assessment result and the second assessment result
The degree of consistency is 85%, is assessed image 11, image 12, image 13 and image 14, is obtained respectively by MS-SSIM method
The score value for obtaining the first assessment result is 78,90,82 and 83, the degree of consistency between the first assessment result and the second assessment result
It is 91%, image 11, image 12, image 13 and image 14 is assessed respectively by VIF method, obtains the first assessment result
Score value be 81,92,83 and 82, the degree of consistency between the first assessment result and the second assessment result is 93%, then according to
The sequence of the degree of consistency from high to low between first assessment result and the second assessment result, preceding 3 consistency selected
Degree is corresponding, and to have reference picture method for evaluating quality be respectively PSNR method, VIF method and MS-SSIM method, other distortions
T are determined in image group has the mode of reference picture method for evaluating quality similar to the above, and details are not described herein again.In this way, can
There is reference picture method for evaluating quality to determine in all distorted image groups that the preceding t degree of consistency is corresponding.It is shown in table 2
The t appraisal procedure selected in all distorted image groups, wherein the appraisal procedure selected in each distorted image group can
, can also be completely not identical with identical, it can also be that part is identical, part is not identical.
Table 2
In determining all distorted image groups the preceding t degree of consistency it is corresponding have reference picture method for evaluating quality it
Afterwards, it will count in all distorted image groups, each frequency for thering is reference picture method for evaluating quality to occur selected, and according to
The sequence of the frequency from high to low, n have reference picture method for evaluating quality before determining.Such as: assuming that n is 3, if distortion class
Selected in the distorted image group that type is a and distortion level is 1 have reference picture method for evaluating quality include PSNR method,
VIF method and MS-SSIM method, if that selects in the distorted image group that type of distortion is a and distortion level is 2 has with reference to figure
As method for evaluating quality includes PSNR method, FSIM method and DLM method, if the distortion that type of distortion is a and distortion level is 3
The reference picture method for evaluating quality that has selected in image group includes SSIM method, VIF method and DLM method, if distortion class
Selected in the distorted image group that type is b and distortion level is 1 have reference picture method for evaluating quality include PSNR method,
VIF method and DLM method, if that selects in the distorted image group that type of distortion is b and distortion level is 2 has reference picture matter
Measuring appraisal procedure includes PSNR method, MS-SSIM method and FSIM method, if the distortion that type of distortion is b and distortion level is 3
The reference picture method for evaluating quality that has selected in image group includes SSIM method, VIF method and PSNR method, then all
The sequence of the frequency for having reference picture method for evaluating quality to occur selected in distorted image group from high to low is successively are as follows: PSNR
Method (5 times), VIF method (4 times), DLM method (3 times), MS-SSIM method (2 times), FSIM method (2 times) and SSIM method
(2 times), in this way, can determine that first 3, to have reference picture method for evaluating quality be respectively PSNR method, VIF method and the side DLM
Method.
Step 3034 has reference picture method for evaluating quality according to n, calculates the second mass.
Specifically, server has reference for passing through n respectively after determining that n have reference picture method for evaluating quality
Image quality measure method calculates the quality of each distorted image, obtains multiple third quality, and will by machine learning method
Multiple third quality are weighted processing by machine learning, to obtain the second mass.Wherein, machine learning method can wrap
Include support vector regression (Support Vector Machine；) and support vector regression (Support Vector SVM
Regression；SVR) etc., it is, of course, also possible to include other machine learning methods, as long as multiple third quality can be carried out
Weighted average processing, for the concrete form of machine learning method, this is not restricted for the present embodiment.The n such as determined
It is a to there is reference picture method for evaluating quality collection to be combined into R={ method 1, method 2 ..., method n }, use each method in set R
After assessing distorted image, the third quality of acquisition is Q={ Q1, Q2 ..., Qn }, by SVM or SVR to multiple thirds
Quality is weighted processing, obtains the second mass.
For example, each distorted image is assessed by PSNR method, VIF method and DLM method respectively, is obtained more
Multiple third quality of acquisition are weighted processing by SVM method, so as to obtain the second mass by a third quality.
It should be noted that processing can be weighted using the method for a variety of machine learning, and by each machine learning
The result that method obtains and the result of user's subjective assessment compare, and are obtained according to Performance Evaluation index (PCC, SROCC, RMSE)
To optimal performance appraisal procedure, so as to improve the accuracy of the second Mass Calculation.Wherein, Performance Evaluation index includes Pierre
Inferior linearly dependent coefficient (Pearson Linear Correlation Efficient；PLCC), Spearman rank correlation system
Number (Spearman's Rank Correlation Coefficient；) and root-mean-square error (Root Mean SROCC
Square Error；RMSE) etc..
In the present embodiment, data set can be grouped according to the type of distortion and distortion level of distorted image, from existing m
A to have in reference picture method for evaluating quality, it is accurate for the assessment of the distorted image of different type of distortion and distortion level to select
The higher n method of property, and processing is weighted by machine learning, the quality of distorted image is obtained, so as to improve figure
As the accuracy of quality evaluation.
Additionally, it is appreciated that the execution sequence of above step 302 and step 303 is only a kind of signal.Step 302 with
The differentiation for the sequencing that step 302 is not carried out can first carry out step 302, then execute step 303；It can also first carry out
Step 303, then step 302 is executed；Also the two steps be may be performed simultaneously, the embodiment of the present application is not specially limited this.
Step 304, according to the first mass and the second mass, determine the quality of image.
In the present embodiment, server the first mass for calculating source images and it is corresponding with source images at least one
After second mass of distorted image, according to the first mass and the second mass, it can will determine to need the matter for the image assessed
Amount.
Furthermore it is possible to obtain quality coefficient by the way that the first mass is carried out standardization processing, and by the quality coefficient multiplied by
The result of acquisition is determined as needing the quality for the image assessed, wherein the value of the quality coefficient is greater than or waits by the second mass
In 0.0, and it is less than or equal to 1.0.
Further, server is carrying out quality evaluation according to the method in above steps to every frame image in video
And then combine the time response of the quality evaluation result of every frame image and video, the assessment of video quality can be obtained
As a result.Wherein, time response is frame level kinetic characteristic, such as takes the luminance difference etc. of the pixel of consecutive frame.
The appraisal procedure of video quality provided by the embodiments of the present application, by obtain include at least one source images and with it is each
The training dataset of at least one corresponding distorted image of source images, and the first mass of each source images is calculated, and at least one
Second mass of a distorted image relative to source images determines the quality of image further according to the first mass and the second mass.Due to
The image for needing to assess is determined by calculating the first mass of source images, and according to calculated first mass and the second mass
Quality, so as to avoid needing to carry out quality evaluation under the premise of assuming that the benchmark image chosen is perfect in the prior art
Phenomenon, it is possible thereby to improve the accuracy of video quality assessment.
Fig. 5 is the structural schematic diagram of the assessment Installation practice one of video quality provided by the embodiments of the present application, referring to figure
5, which includes: acquiring unit 11, computing unit 12 and determination unit 13, in which:
Acquiring unit 11 for obtaining training dataset, the training data concentrate include at least one source images and with it is each
At least one corresponding distorted image of the source images；
Computing unit 12 is used to calculate the first mass of each source images；
The computing unit 12 is also used to calculate second matter of at least one described distorted image relative to the source images
Amount；
Determination unit 13 is used to determine the quality of image according to first mass and second mass.
Above-mentioned apparatus can be used for executing the method that above-mentioned corresponding method embodiment provides, specific implementation and technical effect
Similar, which is not described herein again.
Fig. 6 is the structural schematic diagram of the assessment Installation practice two of video quality provided by the embodiments of the present application, referring to figure
6, on the basis of embodiment shown in Fig. 5, the computing unit 12, comprising:
Determine subelement 121 for determining the type of distortion and distortion level of each distorted image；
Subelement 122 is grouped to be used to be grouped each distorted image according to the type of distortion and the distortion level,
Obtain at least one distorted image group, wherein the type of distortion and distortion journey of the distorted image in same distorted image group
It spends all the same；
The determining subelement 121 is also used to according to multiple first assessment results and the second assessment result, has reference from m
N therein is determined in image quality measure method reference picture method for evaluating quality；First assessment result is difference
There is reference picture method for evaluating quality using the m, is obtained after assessing the distorted image in each distorted image group
As a result, second assessment result be user's subjectivity each distorted image is assessed after obtain as a result, m and n
For positive integer, and m is greater than or equal to n；
Computation subunit 123 is used to have reference picture method for evaluating quality according to the n, calculates second mass.
Optionally, the determining subelement 121 is specifically used for:
There is reference picture method for evaluating quality by m, the distorted image in each distorted image group is carried out respectively
Assessment obtains multiple first assessment results；
In each distorted image group, according to multiple first assessment results, there is reference picture quality to comment from the m
Estimate and determines that t therein has reference picture method for evaluating quality in method；The t have reference picture method for evaluating quality be by
Have according to m consistent between corresponding first assessment result of reference picture method for evaluating quality and second assessment result
The sequence of property degree from high to low, the preceding t similarity selected is corresponding reference picture method for evaluating quality；
Have in reference picture method for evaluating quality according to corresponding the t of all distorted image groups and each have reference
The sequence of the frequency that image quality measure method occurs from high to low, n have reference picture method for evaluating quality before determining；Its
In, t is the positive integer less than or equal to m, and more than or equal to n.
Optionally, the computation subunit 123 is specifically used for:
The quality for having reference picture method for evaluating quality to calculate the distorted image by n respectively, obtains multiple thirds
Quality；
The multiple third quality is weighted processing by machine learning, obtains second mass.
Optionally, the computing unit 123 is specifically used for:
According to the pixel domain of each source images, first mass is calculated.
Optionally, the determination unit 13 is specifically used for:
First mass is subjected to standardization processing, obtains quality coefficient, the value of the quality coefficient is greater than or equal to
0.0, and it is less than or equal to 1.0；
By the quality coefficient multiplied by second mass, and the result of acquisition is determined as to the quality of described image.
Above-mentioned apparatus can be used for executing the method that above-mentioned corresponding method embodiment provides, specific implementation and technical effect
Similar, which is not described herein again.
It should be noted that it should be understood that the division of each unit of the assessment device of the above video quality is only that one kind is patrolled
The division for collecting function, can completely or partially be integrated on a physical entity in actual implementation, can also be physically separate.And
These units can be realized all by way of processing element calls with software；It can also all realize in the form of hardware；
It can realize that unit passes through formal implementation of hardware by way of software is called by processing element with unit.
For example, acquiring unit can be the processing element individually set up, it also can integrate and realized in some chip of server, this
Outside, it can also be stored in the form of program in the memory of server, be called and held by some processing element of server
The function of the row acquiring unit.The realization of other units is similar therewith.Furthermore these units completely or partially can integrate one
It rises, can also independently realize.Computing unit described here can be a kind of integrated circuit, the processing capacity with signal.?
During realization, each step or above each unit of the above method can pass through the integration logic of the hardware in processor elements
The instruction of circuit or software form is completed.
The above unit can be arranged to implement one or more integrated circuits of above method, such as: one
Or multiple specific integrated circuits (Application Specific Integrated Circuit, ASIC), or, one or more
A microprocessor (digital signal processor, DSP), or, one or more field programmable gate array
(Field Programmable Gate Array, FPGA) etc..For another example, when some above unit dispatches journey by processing element
When the form of sequence is realized, which can be general processor, such as central processing unit (Central Processing
Unit, CPU) or it is other can be with the processor of caller.For another example, these units can integrate together, with system on chip
The form of (system-on-a-chip, SOC) is realized.
Fig. 7 A is a kind of possible structural schematic diagram of the application server.Referring to shown in Fig. 7 A, which is wrapped
It includes: processing unit 702 and communication unit 703.Processing unit 702 is for carrying out control management, example to the movement of server 700
Such as, processing unit 702 be used for support server 700 execute aforementioned video quality appraisal procedure embodiment in each step and/
Or other processes for technology described herein.Communication unit 703 is for supporting server 700 and other network entities
Communication, such as the communication between terminal device.Server 700 can also include storage unit 701, be used for storage server
700 program code and data.
Wherein, processing unit 702 can be processor or controller, such as can be central processing unit (Central
Processing Unit, CPU), general processor, digital signal processor (Digital Signal Processor, DSP),
Specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array
It is (Field Programmable Gate Array, FPGA) or other programmable logic device, transistor logic, hard
Part component or any combination thereof.It may be implemented or execute to combine and various illustratively patrol described in present disclosure
Collect box, module and circuit.The processor is also possible to realize the combination of computing function, such as includes one or more micro- places
Manage device combination, DSP and the combination of microprocessor etc..Communication unit 703 can be communication interface, transceiver, transmission circuit etc.,
Wherein, communication interface is to be referred to as, and may include one or more interfaces.Storage unit 701 can be memory.
When processing unit 702 is processor, communication unit 703 is communication interface, when storage unit 701 is memory, this
Server involved in applying can be server shown in Fig. 7 B.
Referring to shown in Fig. 7 B, which includes: processor 712, communication interface 713, memory 711.Optionally,
Server 710 can also include bus 714.Wherein, communication interface 713, processor 712 and memory 711 can be by total
Line 714 is connected with each other；Bus 714 can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect；PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture；EISA) bus etc..The bus 714 can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, Fig. 7 B, it is not intended that an only bus or a type of bus.
Wherein, memory 711 is for storing the instruction that can be executed by processor 712, and processor 712 is for calling memory
The instruction stored in 711, each step in appraisal procedure to execute aforementioned video quality.
The application also provides a kind of assessment system of video quality, including video quality described in any embodiment as above
Assess device.
The application also provides a kind of storage medium, comprising: readable storage medium storing program for executing and computer program, the computer program
For realizing the appraisal procedure for the video quality that aforementioned any embodiment provides.
The application also provides a kind of program product, which includes computer program (executing instruction), the calculating
Machine program is stored in readable storage medium storing program for executing.At least one processor of server can read the calculating from readable storage medium storing program for executing
Machine program, at least one processor execute the video that the computer program provides the aforementioned various embodiments of server implementation
The appraisal procedure of quality.
The embodiment of the present application also provides a kind of assessment device of video quality, including at least one memory element and at least
One processing element, at least one described memory element are for storing program, which is performed, so that the video quality
Assessment device execute the operation of the server in any of the above-described embodiment.
Realizing all or part of the steps of above-mentioned each method embodiment, this can be accomplished by hardware associated with program instructions.
Program above-mentioned can store in a readable access to memory.When being executed, execute includes above-mentioned each method embodiment to the program
The step of；And memory (storage medium) above-mentioned includes: read-only memory (read-only memory, ROM), RAM, quick flashing
Memory, hard disk, solid state hard disk, tape (magnetic tape), floppy disk (floppy disk), CD (optical disc)
And any combination thereof.
Claims (10)
1. a kind of appraisal procedure of video quality characterized by comprising
Training dataset is obtained, it includes at least one source images and corresponding extremely with each source images that the training data, which is concentrated,
A few distorted image；
Calculate the first mass of each source images；
Calculate second mass of at least one described distorted image relative to the source images；
According to first mass and second mass, the quality of image is determined；
Second mass that at least one described distorted image is calculated relative to the source images, comprising:
Determine the type of distortion and distortion level of each distorted image；
According to the type of distortion and the distortion level, each distorted image is grouped, obtains at least one distorted image
Group, wherein the type of distortion and distortion level of the distorted image in same distorted image group are all the same；
According to multiple first assessment results and the second assessment result, has in reference picture method for evaluating quality from m and determine wherein
N have reference picture method for evaluating quality；First assessment result is to be respectively adopted the m to have reference picture quality to comment
Estimate method, it is being obtained after assessing the distorted image in each distorted image group as a result, second assessment result is
It is that user's subjectivity obtains after assessing each distorted image as a result, m and n be positive integer, and m be greater than or equal to n；
There is reference picture method for evaluating quality according to the n, calculates second mass.
2. the method according to claim 1, wherein described tie according to multiple first assessment results and the second assessment
Fruit has in reference picture method for evaluating quality from m and determines that n therein has reference picture method for evaluating quality, comprising:
There is reference picture method for evaluating quality by m, the distorted image in each distorted image group assessed respectively,
Obtain multiple first assessment results；
In each distorted image group, according to multiple first assessment results, there is reference picture quality evaluation side from the m
T therein is determined in method reference picture method for evaluating quality；It is according to m that the t, which have reference picture method for evaluating quality,
A consistency having between corresponding first assessment result of reference picture method for evaluating quality and second assessment result
The sequence of degree from high to low, the preceding t degree of consistency selected is corresponding reference picture method for evaluating quality；
Have in reference picture method for evaluating quality according to corresponding the t of all distorted image groups and each have reference picture
The sequence of the frequency that method for evaluating quality occurs from high to low, n have reference picture method for evaluating quality before determining；Wherein, t
For the positive integer less than or equal to m, and more than or equal to n.
3. method according to claim 1 or 2, which is characterized in that described to have reference picture quality evaluation according to the n
Method calculates second mass, comprising:
The quality for having reference picture method for evaluating quality to calculate the distorted image by n respectively, obtains multiple third quality；
The multiple third quality is weighted processing by machine learning, obtains second mass.
4. method according to claim 1 or 2, which is characterized in that first mass for calculating each source images, packet
It includes:
According to the pixel domain information of each source images, first mass is calculated.
5. method according to claim 1 or 2, which is characterized in that described according to first mass and second matter
Amount, determines the quality of image, comprising:
First mass is subjected to standardization processing, obtains quality coefficient, the value of the quality coefficient is greater than or equal to 0.0, and
Less than or equal to 1.0；
By the quality coefficient multiplied by second mass, and the result of acquisition is determined as to the quality of described image.
6. a kind of assessment device of video quality characterized by comprising
Acquiring unit, for obtaining training dataset, the training data concentrate include at least one source images and with it is each described
At least one corresponding distorted image of source images；
Computing unit, for calculating the first mass of each source images；
The computing unit is also used to calculate second mass of at least one described distorted image relative to the source images；
Determination unit, for determining the quality of image according to first mass and second mass；
The computing unit, comprising:
Subelement is determined, for determining the type of distortion and distortion level of each distorted image；
It is grouped subelement, for being grouped to each distorted image according to the type of distortion and the distortion level, is obtained extremely
A few distorted image group, wherein the type of distortion and distortion level of the distorted image in same distorted image group are homogeneous
Together；
The determining subelement, is also used to according to multiple first assessment results and the second assessment result, has reference picture matter from m
Determine that n therein has reference picture method for evaluating quality in amount appraisal procedure；First assessment result is is respectively adopted
Stating m has reference picture method for evaluating quality, the knot obtained after assessing the distorted image in each distorted image group
Fruit, second assessment result be user's subjectivity each distorted image is assessed after obtain as a result, m and n be positive it is whole
Number, and m is greater than or equal to n；
Computation subunit calculates second mass for having reference picture method for evaluating quality according to the n.
7. device according to claim 6, which is characterized in that the determining subelement is specifically used for:
There is reference picture method for evaluating quality by m, the distorted image in each distorted image group assessed respectively,
Obtain multiple first assessment results；
In each distorted image group, according to multiple first assessment results, there is reference picture quality evaluation side from the m
T therein is determined in method reference picture method for evaluating quality；It is according to m that the t, which have reference picture method for evaluating quality,
A consistency having between corresponding first assessment result of reference picture method for evaluating quality and second assessment result
The sequence of degree from high to low, the preceding t similarity selected is corresponding reference picture method for evaluating quality；
Have in reference picture method for evaluating quality according to corresponding the t of all distorted image groups and each have reference picture
The sequence of the frequency that method for evaluating quality occurs from high to low, n have reference picture method for evaluating quality before determining；Wherein, t
For the positive integer less than or equal to m, and more than or equal to n.
8. device according to claim 6 or 7, which is characterized in that the computation subunit is specifically used for:
The quality for having reference picture method for evaluating quality to calculate the distorted image by n respectively, obtains multiple third quality；
The multiple third quality is weighted processing by machine learning, obtains second mass.
9. device according to claim 6 or 7, which is characterized in that the computing unit is specifically used for:
According to the pixel domain information of each source images, first mass is calculated.
10. device according to claim 6 or 7, which is characterized in that the determination unit is specifically used for:
First mass is subjected to standardization processing, obtains quality coefficient, the value of the quality coefficient is greater than or equal to 0.0, and
Less than or equal to 1.0；
By the quality coefficient multiplied by second mass, and the result of acquisition is determined as to the quality of described image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710725869.6A CN107659806B (en) | 2017-08-22 | 2017-08-22 | The appraisal procedure and device of video quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710725869.6A CN107659806B (en) | 2017-08-22 | 2017-08-22 | The appraisal procedure and device of video quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107659806A CN107659806A (en) | 2018-02-02 |
| CN107659806B true CN107659806B (en) | 2019-08-16 |
Family
ID=61128606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710725869.6A Active CN107659806B (en) | 2017-08-22 | 2017-08-22 | The appraisal procedure and device of video quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107659806B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11089359B1 (en) * | 2019-05-12 | 2021-08-10 | Facebook, Inc. | Systems and methods for persisting in-band metadata within compressed video files |
| CN110290381B (en) * | 2019-08-01 | 2020-10-30 | 字节跳动(香港)有限公司 | Video quality evaluation method and device, electronic equipment and computer storage medium |
| CN111062914B (en) * | 2019-11-28 | 2023-05-30 | 重庆中星微人工智能芯片技术有限公司 | Method, apparatus, electronic device and computer readable medium for acquiring facial image |
| CN111163338B (en) * | 2019-12-27 | 2022-08-12 | 广州市百果园网络科技有限公司 | Video definition evaluation model training method, video recommendation method and related device |
| CN111935545B (en) * | 2020-08-03 | 2023-03-24 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device and equipment for transcoding video data and storage medium |
| CN112616051B (en) * | 2020-12-23 | 2023-05-05 | 北京金山云网络技术有限公司 | Video quality comparison method and device, storage medium and electronic equipment |
| CN113658093A (en) * | 2021-06-30 | 2021-11-16 | 浙江大华技术股份有限公司 | Image quality evaluation method, device, equipment and computer storage medium |
| CN114627085A (en) * | 2022-03-17 | 2022-06-14 | 腾讯科技（深圳）有限公司 | Target image identification method and device, storage medium and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1727375A1 (en) * | 2005-05-27 | 2006-11-29 | Psytechnics Limited | Assessment of perceived quality of a packetized video stream |
| CN101635846A (en) * | 2008-07-21 | 2010-01-27 | 华为技术有限公司 | Method, system and device for evaluating video quality |
| CN102204265A (en) * | 2010-12-31 | 2011-09-28 | 华为技术有限公司 | Method, terminal, server, and system for evaluating video quality |
| CN102202227A (en) * | 2011-06-21 | 2011-09-28 | 珠海世纪鼎利通信科技股份有限公司 | No-reference objective video quality assessment method |
| JP2011205253A (en) * | 2010-03-24 | 2011-10-13 | Nippon Telegr & Teleph Corp <Ntt> | Device, method, and program for transcoded video quality objective evaluation |
| CN103338379A (en) * | 2013-06-05 | 2013-10-02 | 宁波大学 | Stereoscopic video objective quality evaluation method based on machine learning |
| CN103379360A (en) * | 2012-04-23 | 2013-10-30 | 华为技术有限公司 | Assessment method and device for video quality |
| CN106412571A (en) * | 2016-10-12 | 2017-02-15 | 天津大学 | Video quality evaluation method based on gradient similarity standard deviation |
-
2017
- 2017-08-22 CN CN201710725869.6A patent/CN107659806B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1727375A1 (en) * | 2005-05-27 | 2006-11-29 | Psytechnics Limited | Assessment of perceived quality of a packetized video stream |
| CN101635846A (en) * | 2008-07-21 | 2010-01-27 | 华为技术有限公司 | Method, system and device for evaluating video quality |
| JP2011205253A (en) * | 2010-03-24 | 2011-10-13 | Nippon Telegr & Teleph Corp <Ntt> | Device, method, and program for transcoded video quality objective evaluation |
| CN102204265A (en) * | 2010-12-31 | 2011-09-28 | 华为技术有限公司 | Method, terminal, server, and system for evaluating video quality |
| CN102202227A (en) * | 2011-06-21 | 2011-09-28 | 珠海世纪鼎利通信科技股份有限公司 | No-reference objective video quality assessment method |
| CN103379360A (en) * | 2012-04-23 | 2013-10-30 | 华为技术有限公司 | Assessment method and device for video quality |
| CN103338379A (en) * | 2013-06-05 | 2013-10-02 | 宁波大学 | Stereoscopic video objective quality evaluation method based on machine learning |
| CN106412571A (en) * | 2016-10-12 | 2017-02-15 | 天津大学 | Video quality evaluation method based on gradient similarity standard deviation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107659806A (en) | 2018-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107659806B (en) | The appraisal procedure and device of video quality | |
| KR100731358B1 (en) | Method and system for measuring the video quality | |
| EP1924101B1 (en) | Video communication quality estimation device, method, and program | |
| CN103093419B (en) | A kind of method of detected image sharpness and device | |
| CN111355950A (en) | Video transmission quality detection method and system in real-time video communication | |
| CN101616315A (en) | A kind of method for evaluating video quality, device and system | |
| CN103067671B (en) | A kind of method and device showing image | |
| CN105100784A (en) | Smoothness test method and device | |
| CN110139102B (en) | Method, device, equipment and storage medium for predicting video coding complexity | |
| JP7046073B2 (en) | Real-time data processing method and equipment | |
| CN108961345A (en) | A kind of effective determination method and determining device of color in Urine test paper | |
| KR20130107687A (en) | Apparatus for monitoring video quality and method thereof | |
| Seybold et al. | Towards an evaluation of denoising algorithms with respect to realistic camera noise | |
| CN101389045A (en) | Image quality evaluation method and device | |
| CN103428523A (en) | Method and device for estimating video quality | |
| Rousselot et al. | Quality metric aggregation for HDR/WCG images | |
| CN104103065A (en) | No-reference fuzzy image quality evaluation method based on singular value decomposition | |
| Ak et al. | The effect of temporal sub-sampling on the accuracy of volumetric video quality assessment | |
| CN101895787B (en) | Method and system for subjectively evaluating video coding performance | |
| Barkowsky et al. | Subjective experiment dataset for joint development of hybrid video quality measurement algorithms | |
| CN109600604B (en) | Contrast testing method, device and computer readable storage medium | |
| US11255705B2 (en) | Method for setting quality thresholds of products for testing purposes and device employing method | |
| Lukeš et al. | Performance evaluation of image quality metrics with respect to their use for super-resolution enhancement | |
| Alvarez et al. | A flexible QoE framework for video streaming services | |
| Barkowsky et al. | Perceptually motivated spatial and temporal integration of pixel based video quality measures |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220208 Address after: 550025 Huawei cloud data center, jiaoxinggong Road, Qianzhong Avenue, Gui'an New District, Guiyang City, Guizhou Province Patentee after: Huawei Cloud Computing Technologies Co.,Ltd. Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Patentee before: HUAWEI TECHNOLOGIES Co.,Ltd. |