CN104077563A - Human face recognition method and device - Google Patents
Human face recognition method and device Download PDFInfo
- Publication number
- CN104077563A CN104077563A CN201410240747.4A CN201410240747A CN104077563A CN 104077563 A CN104077563 A CN 104077563A CN 201410240747 A CN201410240747 A CN 201410240747A CN 104077563 A CN104077563 A CN 104077563A
- Authority
- CN
- China
- Prior art keywords
- facial image
- alignment
- appointment
- similarity
- area
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a human face recognition method and device, and belongs to the technical field of human face recognition. The method comprises the steps that a first human face image is obtained, the similarity of the first human face image and a specified human face image is determined, the interference value of the similarity from an interference characteristic of the first human face image and the specified human face image is determined, and the similarity is adjusted according to the interference value. The interference value of the similarity from the interference characteristic of the first human face image and the specified human face image is determined, and the similarity of the first human face image and the specified human face image is adjusted according to the interference value, so that the problem that human faces on the first human face image and the specified human face both wear deep-color-frame glasses, or the human faces on the first human face image and the specified human face have identical or similar haircuts, as a result, two human faces with low similarity are misjudged to be with high similarity is solved. The recognition accuracy is improved.
Description
Technical field
The disclosure relates to face recognition technology field, relates in particular to a kind of face identification method and device.
Background technology
People's face is the main sign that people mutually differentiate, are familiar with, remember, and recognition of face occupies an important position in computer vision, pattern-recognition, multimedia technology research.
In correlation technique, the method for recognition of face is all generally that two width facial images carry out the detection of people's face, positioning feature point, feature extraction successively, and carries out similarity measurement according to the feature of extracting, and obtains for weighing the mark of two width facial image similarities.
In two width facial images, people all has dark frame glasses on the face, or when in two width facial images, people's face has same or analogous hair style, original similarity was not two very high people's faces, probably can be considered to similarity higher, and therefore the accuracy rate of identification is lower.
Summary of the invention
In order to overcome the lower problem of accuracy rate of the identification existing in correlation technique, the disclosure provides a kind of face identification method and device.Described technical scheme is as follows:
According to the first aspect of disclosure embodiment, a kind of face identification method is provided, be applicable to judge the similarity of two facial images, comprising:
Obtain the first facial image;
Determine the similarity of described the first facial image and appointment facial image;
The interference value of the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
According to described interference value, adjust described similarity.
In the possible implementation of the first of the present disclosure, the interference value of the interference characteristic of described definite described the first facial image and described appointment facial image to described similarity, comprising:
Described the first facial image and described appointment facial image are alignd with the average shape model of setting respectively;
Respectively the described appointment facial image after described the first facial image after alignment and alignment is carried out to skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment;
According to the non-area of skin color of described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity.
In the possible implementation of the second of the present disclosure, described described appointment facial image to described the first facial image after alignment and after aliging respectively carries out skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment, comprising:
Choose in the described appointment facial image after described the first facial image after alignment and alignment, the region corresponding with setting area of skin color in described average shape faceform is the first area of skin color;
Extract the features of skin colors of described the first area of skin color, and by the described appointment facial image after described the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of described the first area of skin color is defined as the second area of skin color;
By in the described appointment facial image after described the first facial image after alignment and alignment, All Ranges except described the first area of skin color and described the second area of skin color, as the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment.
In the third possible implementation of the present disclosure, described according to the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity, comprising:
Respectively the eigenwert of the pixel of the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as 0;
Described appointment facial image after described the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that described appointment facial image after described the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after described the first facial image or align after the total ratio of pixel of described appointment facial image, the interference value of the interference characteristic that obtains described the first facial image and described appointment facial image to similarity.
In the 4th kind of possible implementation of the present disclosure, described according to described interference value, adjust described similarity, comprising:
According to predetermined funtcional relationship, according to described interference value, determine the modified value of described similarity;
Described similarity is deducted to described modified value, the described similarity after being adjusted.
According to the second aspect of disclosure embodiment, a kind of face identification device is provided, be applicable to judge the similarity of two facial images, comprising:
Acquisition module, for obtaining the first facial image;
Identification module, for determining the similarity of described the first facial image and appointment facial image;
Disturb determination module, the interference value for the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
Correcting module, for according to described interference value, adjusts described similarity.
In the possible implementation of the first of the present disclosure, described interference determination module comprises:
Alignment unit, for aliging described the first facial image and described appointment facial image respectively with the average shape model of setting;
Region determining unit, for respectively the described appointment facial image after described the first facial image after alignment and alignment being carried out to skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment;
Interference calculation unit, for according to the non-area of skin color of described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity.
In the possible implementation of the second of the present disclosure, described region determining unit is used for,
Choose in the described appointment facial image after described the first facial image after alignment and alignment, the region corresponding with setting area of skin color in described average shape faceform is the first area of skin color;
Extract the features of skin colors of described the first area of skin color, and by the described appointment facial image after described the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of described the first area of skin color is defined as the second area of skin color;
By in the described appointment facial image after described the first facial image after alignment and alignment, All Ranges except described the first area of skin color and described the second area of skin color, as the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment.
In the third possible implementation of the present disclosure, described interference calculation unit is used for,
Respectively the eigenwert of the pixel of the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as 0;
Described appointment facial image after described the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that described appointment facial image after described the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after described the first facial image or align after the total ratio of pixel of described appointment facial image, the interference value of the interference characteristic that obtains described the first facial image and described appointment facial image to similarity.
In the 4th kind of possible implementation of the present disclosure, described correcting module comprises:
Modified value determining unit, for the funtcional relationship according to predetermined, according to described interference value, determines the modified value of described similarity;
Score calculating unit, for described similarity is deducted to described modified value, the described similarity after being adjusted.
According to the third aspect of disclosure embodiment, a kind of face identification device is provided, be applicable to judge the similarity of two facial images, comprising:
Processor;
Storer for storage of processor executable instruction;
Wherein, described processor is configured to:
Obtain the first facial image;
Determine the similarity of described the first facial image and appointment facial image;
The interference value of the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
According to described interference value, adjust described similarity.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the interference value by the interference characteristic determining the first facial image and specify facial image to similarity, and adjust the first facial image and the similarity of specifying facial image according to this interference value, avoid due to the first facial image and specify people in facial image all to have on the face dark frame glasses, or in the first facial image and appointment facial image, people's face has the reasons such as same or analogous hair style, cause by similarity, not to be that two very high people's faces are mistaken for similarity higher, improved the accuracy rate of identification.
Should be understood that, it is only exemplary and explanatory that above general description and details are hereinafter described, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing is herein merged in instructions and forms the part of this instructions, shows embodiment according to the invention, and is used from and explains principle of the present invention with instructions one.
Fig. 1 is according to the process flow diagram of a kind of face identification method shown in an exemplary embodiment;
Fig. 2 is according to the process flow diagram of the another kind of face identification method shown in an exemplary embodiment;
Fig. 3 is according to the block diagram of a kind of face identification device shown in an exemplary embodiment;
Fig. 4 is according to the block diagram of the another kind of face identification device shown in an exemplary embodiment;
Fig. 5 is according to the block diagram of a kind of face identification device shown in an exemplary embodiment.
Embodiment
Here will at length to exemplary embodiment, describe, its example shown in the accompanying drawings.When description below relates to accompanying drawing, unless separately there is expression, the same numbers in different accompanying drawings represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the present invention.On the contrary, they are only the examples with apparatus and method as consistent in some aspects that described in detail in appended claims, of the present invention.
Fig. 1 is according to the process flow diagram of a kind of face identification method shown in an exemplary embodiment, and as shown in Figure 1, face identification method, for mobile terminal, is applicable to judge the similarity of two facial images, comprises the following steps.
In step S101, obtain the first facial image.
In step S102, determine the similarity of the first facial image and appointment facial image.
In step S103, the interference value of the interference characteristic of determining the first facial image and specifying facial image to similarity.
In the present embodiment, interference characteristic is the feature of the non-face part that in the first facial image and the human face region of specifying facial image, eigenwert is identical.Interference characteristic can comprise dark frame glasses, hair, beard etc., and the disclosure is not restricted this.Interference value is for weighing the annoyance level of interference characteristic to definite similarity.
In step S104, according to interference value, adjust similarity.
Disclosure embodiment is the interference value to similarity by the interference characteristic determining the first facial image and specify facial image, and adjust the first facial image and the similarity of specifying facial image according to this interference value, avoid due to the first facial image and specify people in facial image all to have on the face dark frame glasses, or in the first facial image and appointment facial image, people's face has the reasons such as same or analogous hair style, cause by similarity, not to be that two very high people's faces are mistaken for similarity higher, improved the accuracy rate of identification.
Fig. 2 is according to the process flow diagram of the another kind of face identification method shown in an exemplary embodiment, and as shown in Figure 2, face identification method, for mobile terminal, is applicable to judge the similarity of two facial images, comprises the following steps.
In step S201, obtain the first facial image and the second facial image.
In the present embodiment, the second facial image, for specifying facial image, specifies facial image to obtain from the external world.In other embodiments, specify facial image can be pre-stored in terminal, the disclosure is not restricted this yet.
In a kind of implementation of the present embodiment, this step S201 can comprise:
Obtain two width images;
Respectively two width images are carried out to the detection of people's face, in the piece image in two width images, determine the first facial image, in the another piece image in two width images, determine the second facial image.
In actual applications, two width images are carried out to people's face and detect people's face detection algorithm that can adopt based on Adaboost (Adaptive Boosting, self-adaptation strengthens).First to image according to predetermined ratio successively convergent-divergent, then at the subwindow of the 20*20 of each image pixel, differentiating is successively people's face, or non-face, finally obtains position and the size of people's face in image.According to position and the size of people's face in image, in two width images, intercept, can obtain the first facial image and the second facial image.
In step S202, the first facial image and the second facial image are carried out to recognition of face, obtain the similarity of the first facial image and the second facial image.
In the another kind of implementation of the present embodiment, this step S202 can comprise:
Adopt respectively the positioning feature point algorithm based on ASM (Active Shape Model, active shape model), determine the shape of the first facial image and the shape of the second facial image;
According to the shape of the first facial image, the first facial image is carried out to Gabor (Jia Bai) wavelet transformation, PCA (Principal Component Analysis successively, principal component analysis (PCA)), LDA (Linear Discriminant Analysis, linear discriminant analysis), obtain the characteristic information of the first facial image;
According to the shape of the second facial image, the second facial image is carried out to Gabor wavelet transformation, PCA, LDA, obtain the characteristic information of the second facial image;
Calculate the cosine distance between the characteristic information of the first facial image and the characteristic information of the second facial image, and according to cosine distance, obtain the similarity of the first facial image and the second facial image.
In actual applications, when the positioning feature point algorithm of employing based on ASM determined the shape of facial image, first in image, carry out initial alignment, again for each unique point of initial alignment, according to the gray level model of each unique point, in image, search for the accurate location of each unique point and revise.Through repeatedly searching for and revising, definite shape can reflect people's face preferably.
The similarity of the first facial image and the second facial image can adopt fraction representation, as being divided into full marks with 100, within 90 minutes, represents that it is identical that the first face image and the second facial image have 90% region, and similarity is high.
Understandably, by execution step S202, can realize the similarity of determining the first facial image and specifying facial image.
In step S203, the first facial image and the second facial image are alignd with the average shape model of setting respectively.
In another implementation of the present embodiment, this step S203 can comprise:
According to average shape faceform, the shape of the shape of the first facial image and the second facial image is carried out to two-dimentional affined transformation respectively.
In actual applications, while carrying out two-dimentional affined transformation, only need calculate transfer function for shape and average man's face shape model of people's face.After the shape of the shape of the first facial image and the second facial image is carried out to two-dimentional affined transformation, can obtain the first facial image and the second facial image that size is identical, the first facial image and the second facial image that align with the average shape model of setting.
In step S204, respectively the second facial image after the first facial image after alignment and alignment is carried out to skin analysis, the first facial image after definite alignment and the non-area of skin color of the second facial image after alignment.
In another implementation of the present disclosure, this step S204 can comprise:
Choose respectively in the second facial image after the first facial image after alignment and alignment, the region corresponding with setting area of skin color in average shape faceform is the first area of skin color;
Extract respectively the features of skin colors of the first area of skin color, and by the second facial image after the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of the first area of skin color is defined as the second area of skin color;
By in the second facial image after the first facial image after alignment and alignment, the All Ranges except the first area of skin color and the second area of skin color, as the non-area of skin color of the second facial image after the first facial image after alignment and alignment respectively.
Understandably, the probability that the cheek position in people's face is area of skin color is larger, therefore can be using the cheek position in people's face as setting area of skin color.In actual applications, the unique point of cheek part in average shape faceform can be demarcated as setting area of skin color.
In step S205, according to the non-area of skin color of the second facial image after the first facial image after alignment and alignment, the interference value of the interference characteristic of calculating the first facial image and the second facial image to similarity.
In the present embodiment, interference characteristic is the feature of the non-face part that in the human face region of the first facial image and the second facial image, eigenwert is identical.Interference characteristic can comprise dark frame glasses, hair, beard etc., and the disclosure is not restricted this.Interference value is for weighing the annoyance level of interference characteristic to definite similarity.
In another implementation of the present disclosure, this step S205 can comprise:
Respectively the eigenwert of the pixel of the non-area of skin color of the second facial image after the first facial image after alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the second facial image after the first facial image after alignment and alignment is taken as 0;
The second facial image after the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that the second facial image after the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after the first facial image or align after the total ratio of pixel of the second facial image, the interference value of the interference characteristic that obtains the first facial image and the second facial image to similarity.
In the present embodiment, the area of skin color of the second facial image after the first facial image after alignment and alignment comprises the first area of skin color and the second area of skin color.
Understandably, by performing step successively S203-S205, can realize the interference characteristic determining the first facial image and the specify facial image interference value to similarity.
In step S206, according to interference value, adjust similarity.
In another implementation of the present disclosure, this step S206 can comprise:
According to predetermined funtcional relationship, according to interference value, determine the modified value of similarity;
Similarity is deducted to modified value, the similarity after being adjusted.
For example, the total ratio of the quantity that statistics obtains and the pixel of the first facial image or the second facial image is 80%, and similarity is 90 minutes, modified value is decided to be to 50 minutes, similarity after the adjustment of the first facial image and the second facial image is to deduct 50 minutes in 90 minutes, 40 minutes.And for example, the total ratio of the quantity that statistics obtains and the pixel of the first facial image or the second facial image is 20%, and similarity is 80 minutes, modified value is decided to be to 10 minutes, similarity after the adjustment of the first facial image and the second facial image is to deduct 10 minutes in 80 minutes, 70 minutes.
Disclosure embodiment is the interference value to similarity by the interference characteristic determining the first facial image and specify facial image, and adjust the first facial image and the similarity of specifying facial image according to this interference value, avoid due to the first facial image and specify people in facial image all to have on the face dark frame glasses, or in the first facial image and appointment facial image, people's face has the reasons such as same or analogous hair style, cause by similarity, not to be that two very high people's faces are mistaken for similarity higher, improved the accuracy rate of identification.
Fig. 3 is according to the block diagram of a kind of face identification device shown in an exemplary embodiment, is applicable to judge the similarity of two facial images, and as shown in Figure 3, this device comprises acquisition module 301, identification module 302, disturbs determination module 303 and correcting module 304.
This acquisition module 301 is configured to obtain the first facial image.
The similarity that this identification module 302 is configured to determine the first facial image and specifies facial image.
This interference determination module 303 is configured to the interference characteristic determining the first facial image and the specify facial image interference value to similarity.
This correcting module 304 is configured to according to interference value, adjusts similarity.
Disclosure embodiment is the interference value to similarity by the interference characteristic determining the first facial image and specify facial image, and adjust the first facial image and the similarity of specifying facial image according to this interference value, avoid due to the first facial image and specify people in facial image all to have on the face dark frame glasses, or in the first facial image and appointment facial image, people's face has the reasons such as same or analogous hair style, cause by similarity, not to be that two very high people's faces are mistaken for similarity higher, improved the accuracy rate of identification.
Fig. 4 is according to the block diagram of the another kind of face identification device shown in an exemplary embodiment, be applicable to judge the similarity of two facial images, as shown in Figure 4, this device comprises acquisition module 401, identification module 402, disturbs determination module 403 and correcting module 404.
This acquisition module 401 is configured to obtain the first facial image.
The similarity that this identification module 402 is configured to determine the first facial image and specifies facial image.
This interference determination module 403 is configured to the interference characteristic determining the first facial image and the specify facial image interference value to similarity.
This correcting module 404 is configured to according to interference value, adjusts similarity.
In a kind of implementation of the present embodiment, this interference determination module 403 can comprise alignment unit 4031, region determining unit 4032 and interference calculation unit 4033.
This alignment unit 4031 is configured to the first facial image and specifies facial image to align with the average shape model of setting respectively.
This region determining unit 4032 is configured to respectively the appointment facial image after the first facial image after alignment and alignment be carried out to skin analysis, the first facial image after definite alignment and the non-area of skin color of the appointment facial image after alignment.
This interference calculation unit 4033 is configured to according to the non-area of skin color of the first facial image after aliging and the appointment facial image after alignment, the interference value of the interference characteristic of calculating the first facial image and appointment facial image to similarity.
This region determining unit 4032 can be for,
Choose in the appointment facial image after the first facial image after alignment and alignment, the region corresponding with setting area of skin color in average shape faceform is the first area of skin color;
Extract the features of skin colors of the first area of skin color, and by the appointment facial image after the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of the first area of skin color is defined as the second area of skin color;
By in the appointment facial image after the first facial image after alignment and alignment, the All Ranges except the first area of skin color and the second area of skin color, as the non-area of skin color of the appointment facial image after the first facial image after alignment and alignment.
This interference calculation unit 4033 can be for,
Respectively the eigenwert of the pixel of the non-area of skin color of the appointment facial image after the first facial image after alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the appointment facial image after the first facial image after alignment and alignment is taken as 0;
Appointment facial image after the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that appointment facial image after the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after the first facial image or align after the total ratio of pixel of appointment facial image, the interference value of the interference characteristic that obtains the first facial image and specify facial image to similarity.
In the another kind of implementation of the present embodiment, this correcting module 404 can comprise modified value determining unit 4041 and score calculating unit 4042.
This modified value determining unit 4041 is configured to according to predetermined funtcional relationship, according to interference value, determines the modified value of similarity.
This score calculating unit 4042 is configured to similarity to deduct modified value, the similarity after being adjusted.
Disclosure embodiment is the interference value to similarity by the interference characteristic determining the first facial image and specify facial image, and adjust the first facial image and the similarity of specifying facial image according to this interference value, avoid due to the first facial image and specify people in facial image all to have on the face dark frame glasses, or in the first facial image and appointment facial image, people's face has the reasons such as same or analogous hair style, cause by similarity, not to be that two very high people's faces are mistaken for similarity higher, improved the accuracy rate of identification.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations have been described in detail in the embodiment of relevant the method, will not elaborate explanation herein.
Fig. 5 is according to the block diagram of a kind of device 800 for face identification method shown in an exemplary embodiment.For example, device 800 can be mobile phone, computing machine, digital broadcast terminal, information receiving and transmitting equipment, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Fig. 5, device 800 can comprise following one or more assembly: processing components 802, storer 804, power supply module 806, multimedia groupware 808, audio-frequency assembly 810, I/O (Input/Output, I/O) interface 812, sensor module 814, and communications component 816.
The integrated operation of processing components 802 common control device 800, such as with demonstration, call, data communication, the operation that camera operation and record operation are associated.Treatment element 802 can comprise that one or more processors 820 carry out instruction, to complete all or part of step of above-mentioned method.In addition, processing components 802 can comprise one or more modules, is convenient to mutual between processing components 802 and other assemblies.For example, processing element 802 can comprise multi-media module, to facilitate mutual between multimedia groupware 808 and processing components 802.
Storer 804 is configured to store various types of data to be supported in the operation of equipment 800.The example of these data comprises for any application program of operation on device 800 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 804 can be realized by the volatibility of any type or non-volatile memory device or their combination, as SRAM (Static Random Access Memory, static RAM), EEPROM (Electrically Erasable Programmable Read-Only Memory, Electrically Erasable Read Only Memory), EPROM (Erasable Programmable Read Only Memory, Erasable Programmable Read Only Memory EPROM), PROM (Programmable Read-Only Memory, programmable read only memory), ROM (Read-Only Memory, ROM (read-only memory)), magnetic store, flash memory, disk or CD.
Electric power assembly 806 provides electric power for installing 800 various assemblies.Electric power assembly 806 can comprise power-supply management system, one or more power supplys, and other and the assembly that generates, manages and distribute electric power to be associated for device 800.
Multimedia groupware 808 is included in the screen that an output interface is provided between this device 800 and user.In certain embodiments, screen can comprise LCD (Liquid Crystal Display, liquid crystal display) and TP (Touch Panel, touch panel).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises that one or more touch sensors are with the gesture on sensing touch, slip and touch panel.This touch sensor is the border of sensing touch or sliding action not only, but also detects duration and the pressure relevant to this touch or slide.In certain embodiments, multimedia groupware 808 comprises a front-facing camera and/or post-positioned pick-up head.When equipment 800 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to output and/or input audio signal.For example, audio-frequency assembly 810 comprises a MIC (Microphone, microphone), and when device 800 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal receiving can be further stored in storer 804 or be sent via communications component 816.In certain embodiments, audio-frequency assembly 810 also comprises a loudspeaker, for output audio signal.
I/O interface 812 is for providing interface between processing components 802 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 814 comprises one or more sensors, is used to device 800 that the state estimation of various aspects is provided.For example, sensor module 814 can detect the opening/closing state of equipment 800, the relative positioning of assembly, for example this assembly is display and the keypad of device 800, the position of all right pick-up unit 800 of sensor module 814 or 800 1 assemblies of device changes, user is with device 800 existence that contact or do not have the temperature variation of device 800 orientation or acceleration/deceleration and device 800.Sensor module 814 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 814 can also comprise optical sensor, as CMOS (Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductor (CMOS)) or CCD (Charge-coupled Device, charge coupled cell) imageing sensor, for using in imaging applications.In certain embodiments, this sensor module 814 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 816 is configured to be convenient to the communication of wired or wireless mode between device 800 and other equipment.Device 800 wireless networks that can access based on communication standard, as WiFi (Wireless Fidelity, adopting wireless fidelity technology), 2G (Second Generation mobile communication technology, second generation mobile communication technology) or 3G (3rd Generation mobile communication technology, or their combination third generation mobile technology).In one exemplary embodiment, communication component 816 receives broadcast singal or the broadcast related information from external broadcasting management system via broadcast channel.In one exemplary embodiment, this communication component 816 also comprises NFC (Near Field Communication, near-field communication) module, to promote junction service.For example, can be based on RFID (Radio Frequency Identification in NFC module, radio-frequency (RF) identification) technology, IrDA (Infrared Data Association, Infrared Data Association) technology, UWB (Ultra Wideband, ultra broadband) technology, BT (Blue Tooth, bluetooth) technology and other technologies realize.
In the exemplary embodiment, device 800 can be by one or more ASIC (Application Specific Integrated Circuit, application specific integrated circuit), DSP (Digital Signal Processing, digital signal processor), DSPD (Digital Signal Processing Device, digital signal processing appts), PLD (Programmable Logic Device, programmable logic device (PLD)), FPGA (Field-Programmable Gate Array, field programmable gate array), controller, microcontroller, microprocessor or other electronic components are realized, be used for carrying out said method.
In the exemplary embodiment, also provide a kind of non-provisional computer-readable recording medium that comprises instruction, for example, comprised the storer 804 of instruction, above-mentioned instruction can have been carried out said method by the processor 820 of device 800.For example, this non-provisional computer-readable recording medium can be ROM, RAM (Ramdom Access Memory, random access memory), CD-ROM (Compact Disc Read-Only Memory, compact disc read-only memory), tape, floppy disk and optical data storage equipment etc.
A non-provisional computer-readable recording medium, when the instruction in this storage medium is carried out by the processor of terminal (intelligent television), makes terminal can carry out a kind of face identification method, and the method comprises:
Obtain the first facial image;
Determine the similarity of the first facial image and appointment facial image;
The interference value of the interference characteristic of determining the first facial image and specifying facial image to similarity;
According to interference value, adjust similarity.
In a kind of implementation of the present embodiment, the interference value of the interference characteristic of determining the first facial image and specifying facial image to similarity, comprising:
The first facial image and appointment facial image are alignd with the average shape model of setting respectively;
Respectively the appointment facial image after the first facial image after alignment and alignment is carried out to skin analysis, the first facial image after definite alignment and the non-area of skin color of the appointment facial image after alignment;
According to the non-area of skin color of the first facial image after aliging and the appointment facial image after alignment, the interference value of the interference characteristic of calculating the first facial image and appointment facial image to similarity.
In the another kind of implementation of the present embodiment, respectively the appointment facial image after the first facial image after alignment and alignment is carried out to skin analysis, the first facial image after definite alignment and the non-area of skin color of the appointment facial image after alignment, comprising:
Choose in the appointment facial image after the first facial image after alignment and alignment, the region corresponding with setting area of skin color in average shape faceform is the first area of skin color;
Extract the features of skin colors of the first area of skin color, and by the appointment facial image after the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of the first area of skin color is defined as the second area of skin color;
By in the appointment facial image after the first facial image after alignment and alignment, the All Ranges except the first area of skin color and the second area of skin color, as the non-area of skin color of the appointment facial image after the first facial image after alignment and alignment.
In another implementation of the present embodiment, according to the non-area of skin color of the first facial image after aliging and the appointment facial image after alignment, the interference value of the interference characteristic of calculating the first facial image and appointment facial image to similarity, comprising:
Respectively the eigenwert of the pixel of the non-area of skin color of the appointment facial image after the first facial image after alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the appointment facial image after the first facial image after alignment and alignment is taken as 0;
Appointment facial image after the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that appointment facial image after the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after the first facial image or align after the total ratio of pixel of appointment facial image, the interference value of the interference characteristic that obtains the first facial image and specify facial image to similarity.
In another implementation of the present embodiment, according to interference value, adjust similarity, comprising:
According to predetermined funtcional relationship, according to interference value, determine the modified value of similarity;
Similarity is deducted to modified value, the similarity after being adjusted.
Those skilled in the art, considering instructions and putting into practice after invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised undocumented common practise or the conventional techniques means in the art of the disclosure.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various modifications and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (11)
1. a face identification method, is applicable to judge it is characterized in that the similarity of two facial images, comprising:
Obtain the first facial image;
Determine the similarity of described the first facial image and appointment facial image;
The interference value of the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
According to described interference value, adjust described similarity.
2. method according to claim 1, is characterized in that, the interference value of the interference characteristic of described definite described the first facial image and described appointment facial image to described similarity, comprising:
Described the first facial image and described appointment facial image are alignd with the average shape model of setting respectively;
Respectively the described appointment facial image after described the first facial image after alignment and alignment is carried out to skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment;
According to the non-area of skin color of described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity.
3. method according to claim 2, it is characterized in that, described described appointment facial image to described the first facial image after alignment and after aliging respectively carries out skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment, comprising:
Choose in the described appointment facial image after described the first facial image after alignment and alignment, the region corresponding with setting area of skin color in described average shape faceform is the first area of skin color;
Extract the features of skin colors of described the first area of skin color, and by the described appointment facial image after described the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of described the first area of skin color is defined as the second area of skin color;
By in the described appointment facial image after described the first facial image after alignment and alignment, All Ranges except described the first area of skin color and described the second area of skin color, as the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment.
4. method according to claim 2, it is characterized in that, described according to the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity, comprising:
Respectively the eigenwert of the pixel of the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as 0;
Described appointment facial image after described the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that described appointment facial image after described the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after described the first facial image or align after the total ratio of pixel of described appointment facial image, the interference value of the interference characteristic that obtains described the first facial image and described appointment facial image to similarity.
5. according to the method described in claim 1-4 any one, it is characterized in that, described according to described interference value, adjust described similarity, comprising:
According to predetermined funtcional relationship, according to described interference value, determine the modified value of described similarity;
Described similarity is deducted to described modified value, the described similarity after being adjusted.
6. a face identification device, is applicable to judge it is characterized in that the similarity of two facial images, comprising:
Acquisition module, for obtaining the first facial image;
Identification module, for determining the similarity of described the first facial image and appointment facial image;
Disturb determination module, the interference value for the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
Correcting module, for according to described interference value, adjusts described similarity.
7. device according to claim 6, is characterized in that, described interference determination module comprises:
Alignment unit, for aliging described the first facial image and described appointment facial image respectively with the average shape model of setting;
Region determining unit, for respectively the described appointment facial image after described the first facial image after alignment and alignment being carried out to skin analysis, described the first facial image after definite alignment and the non-area of skin color of the described appointment facial image after alignment;
Interference calculation unit, for according to the non-area of skin color of described appointment facial image after described the first facial image after described alignment and alignment, the interference value of the interference characteristic that calculates described the first facial image and described appointment facial image to similarity.
8. device according to claim 7, is characterized in that, described region determining unit is used for,
Choose in the described appointment facial image after described the first facial image after alignment and alignment, the region corresponding with setting area of skin color in described average shape faceform is the first area of skin color;
Extract the features of skin colors of described the first area of skin color, and by the described appointment facial image after described the first facial image after alignment and alignment, the region that features of skin colors is identical with the features of skin colors of described the first area of skin color is defined as the second area of skin color;
By in the described appointment facial image after described the first facial image after alignment and alignment, All Ranges except described the first area of skin color and described the second area of skin color, as the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment.
9. device according to claim 7, is characterized in that, described interference calculation unit is used for,
Respectively the eigenwert of the pixel of the non-area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as to 1, the eigenwert of the area of skin color of the described appointment facial image after described the first facial image after described alignment and alignment is taken as 0;
Described appointment facial image after described the first facial image after alignment and alignment is carried out to image friendship;
The eigenwert of the pixel that described appointment facial image after described the first facial image after statistics alignment and alignment is corresponding is the quantity of 1 pixel;
The quantity that counting statistics obtains with align after described the first facial image or align after the total ratio of pixel of described appointment facial image, the interference value of the interference characteristic that obtains described the first facial image and described appointment facial image to similarity.
10. according to the device described in claim 6-9 any one, it is characterized in that, described correcting module comprises:
Modified value determining unit, for the funtcional relationship according to predetermined, according to described interference value, determines the modified value of described similarity;
Score calculating unit, for described similarity is deducted to described modified value, the described similarity after being adjusted.
11. 1 kinds of face identification devices, are applicable to judge it is characterized in that the similarity of two facial images, comprising:
Processor;
Storer for storage of processor executable instruction;
Wherein, described processor is configured to:
Obtain the first facial image;
Determine the similarity of described the first facial image and appointment facial image;
The interference value of the interference characteristic of determining described the first facial image and described appointment facial image to described similarity;
According to described interference value, adjust described similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410240747.4A CN104077563B (en) | 2014-05-30 | 2014-05-30 | Face identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410240747.4A CN104077563B (en) | 2014-05-30 | 2014-05-30 | Face identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104077563A true CN104077563A (en) | 2014-10-01 |
| CN104077563B CN104077563B (en) | 2018-02-02 |
Family
ID=51598811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410240747.4A Active CN104077563B (en) | 2014-05-30 | 2014-05-30 | Face identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104077563B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN106919884A (en) * | 2015-12-24 | 2017-07-04 | 北京汉王智远科技有限公司 | Human facial expression recognition method and device |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
| CN107506687A (en) * | 2017-07-17 | 2017-12-22 | 广东欧珀移动通信有限公司 | Biopsy method and Related product |
| CN107683499A (en) * | 2015-06-03 | 2018-02-09 | 索尼公司 | Based on observation identification user and perform the information processor of the function based on user, methods and procedures |
| CN109272006A (en) * | 2017-07-18 | 2019-01-25 | 北京柯斯元科技有限公司 | Anti-counterfeit sign with random texture pattern decision-making system and determination method |
| WO2020258119A1 (en) * | 2019-06-27 | 2020-12-30 | 深圳市汇顶科技股份有限公司 | Face recognition method and apparatus, and electronic device |
| WO2021012647A1 (en) * | 2019-07-24 | 2021-01-28 | 创新先进技术有限公司 | Face verification method and apparatus, server and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
-
2014
- 2014-05-30 CN CN201410240747.4A patent/CN104077563B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107683499A (en) * | 2015-06-03 | 2018-02-09 | 索尼公司 | Based on observation identification user and perform the information processor of the function based on user, methods and procedures |
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN106919884A (en) * | 2015-12-24 | 2017-07-04 | 北京汉王智远科技有限公司 | Human facial expression recognition method and device |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
| CN107506687A (en) * | 2017-07-17 | 2017-12-22 | 广东欧珀移动通信有限公司 | Biopsy method and Related product |
| WO2019015415A1 (en) * | 2017-07-17 | 2019-01-24 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method of living body detection and terminal device |
| CN107506687B (en) * | 2017-07-17 | 2020-01-21 | Oppo广东移动通信有限公司 | Living body detection method and related product |
| RU2731370C1 (en) * | 2017-07-17 | 2020-09-02 | Гуандун Оппо Мобайл Телекоммьюникейшнс Корп., Лтд. | Method of living organism recognition and terminal device |
| US11100348B2 (en) | 2017-07-17 | 2021-08-24 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method of living body detection and terminal device |
| CN109272006A (en) * | 2017-07-18 | 2019-01-25 | 北京柯斯元科技有限公司 | Anti-counterfeit sign with random texture pattern decision-making system and determination method |
| WO2020258119A1 (en) * | 2019-06-27 | 2020-12-30 | 深圳市汇顶科技股份有限公司 | Face recognition method and apparatus, and electronic device |
| WO2021012647A1 (en) * | 2019-07-24 | 2021-01-28 | 创新先进技术有限公司 | Face verification method and apparatus, server and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104077563B (en) | 2018-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104077563A (en) | Human face recognition method and device | |
| CN106454336B (en) | The method and device and terminal that detection terminal camera is blocked | |
| CN103885588B (en) | Automatic switching method and device | |
| CN106503617A (en) | Model training method and device | |
| CN105654420A (en) | Face image processing method and device | |
| CN105512605A (en) | Face image processing method and device | |
| CN106228556B (en) | image quality analysis method and device | |
| CN105302315A (en) | Image processing method and device | |
| CN105469056A (en) | Face image processing method and device | |
| CN112258381A (en) | Model training method, image processing method, device, equipment and storage medium | |
| CN104484858B (en) | Character image processing method and processing device | |
| CN103886284B (en) | Character attribute information identifying method, device and electronic equipment | |
| CN107463903B (en) | Face key point positioning method and device | |
| CN105528078B (en) | The method and device of controlling electronic devices | |
| CN105469356A (en) | Human face image processing method and apparatus thereof | |
| CN105574512A (en) | Method and device for processing image | |
| CN105279499A (en) | Age recognition method and device | |
| CN106355549A (en) | Photographing method and equipment | |
| CN104036240A (en) | Face feature point positioning method and device | |
| CN109145679A (en) | A kind of method, apparatus and system issuing warning information | |
| CN105354560A (en) | Fingerprint identification method and device | |
| CN105357425A (en) | Image shooting method and image shooting device | |
| CN104731688A (en) | Method and device for prompting reading schedule | |
| CN106295499A (en) | Age estimation method and device | |
| CN110717399A (en) | Face recognition method and electronic terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |