CN108876758B - Face recognition method, device and system - Google Patents
Face recognition method, device and system Download PDFInfo
- Publication number
- CN108876758B CN108876758B CN201710700742.9A CN201710700742A CN108876758B CN 108876758 B CN108876758 B CN 108876758B CN 201710700742 A CN201710700742 A CN 201710700742A CN 108876758 B CN108876758 B CN 108876758B
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- image
- condition
- determining
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a face recognition method, a face recognition device and a face recognition system, wherein the method comprises the following steps: receiving a plurality of tracking images obtained by tracking and capturing an object to be identified; determining a face image in each tracking image and a condition parameter value of the face image; determining the quality score of the face image according to the condition parameter value and a preset quality determination function, wherein the quality determination function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image; the method comprises the steps of selecting a face image with a quality score meeting a preset condition for face recognition, determining the face image from a plurality of tracking images captured by tracking, selecting the face image meeting the preset condition from the plurality of face images according to the quality score of the face image, and reducing the operation amount of image recognition and shortening the image recognition time.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a face recognition method, a face recognition device and a face recognition system.
Background
In the process that the pedestrian passes through the entrance guard, the images of the human face can be captured by the camera through continuous multiframes, and then the captured images are identified, so that the passing condition of the pedestrian can be recorded, the passing authority of the pedestrian is verified, the early warning for strange pedestrians is realized, and the like. At present, when a plurality of captured images are compared with a large number of images in a standard base library one by one, the calculation amount is very large, and the time consumption is long.
Disclosure of Invention
In view of the above, the present invention provides a face recognition method, a face recognition device and a face recognition system, so as to alleviate the technical problems of large computation amount and long processing time in the prior art for performing contrast recognition on all captured multi-frame images.
In a first aspect, an embodiment of the present invention provides a face recognition method, including:
receiving a plurality of tracking images obtained by tracking and capturing an object to be identified;
determining a face image in each tracking image and a condition parameter value of the face image;
determining the quality score of the face image according to the condition parameter value and a preset quality determination function, wherein the quality determination function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image;
and selecting the face image with the quality score meeting the preset condition for face recognition.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the condition parameter includes at least one of: the blurring degree of the face image, the three-dimensional deflection angle of the face, the brightness of the face image and the area of the face image.
With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where the determining a quality score of the face image according to the conditional parameter value and a preset quality determination function includes:
aiming at each of a plurality of face images, respectively calculating the mass fraction component of the face image according to the fitting function corresponding to each condition parameter;
and carrying out normalization processing on the product of the quality fraction components of the face image to obtain the quality fraction.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the calculating quality score components of the face images according to the fitting functions corresponding to each of the condition parameters respectively includes:
respectively calculating the mass fraction components of the face images by using a fitting function determined according to the identification accuracy rate distribution corresponding to the condition parameters;
or, respectively calculating the quality fraction components of the face images by using a fitting function determined according to the confidence coefficient distribution corresponding to the condition parameters;
or calculating the quality score component of the face image by using a fitting function determined according to the recognition accuracy distribution corresponding to at least one condition parameter, and calculating the quality score component of the face image by using a fitting function determined according to the confidence coefficient distribution corresponding to other condition parameters.
With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the method further includes:
respectively drawing identification accuracy rate distribution corresponding to each condition parameter according to historical image identification data;
and respectively carrying out data curve fitting on the identification accuracy rate distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters of the face image and the identification accuracy rate distribution.
With reference to the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the method further includes:
respectively drawing confidence coefficient distribution corresponding to each condition parameter according to historical image identification data;
and respectively carrying out data curve fitting on the confidence coefficient distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters and the confidence coefficient distribution of the face image.
With reference to the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the method further includes:
multiplying the fitting functions corresponding to the plurality of condition parameters to obtain an intermediate function;
determining a maximum value and a minimum value of the intermediate function;
determining a normalization coefficient of the quality determination function according to the maximum value and the minimum value;
determining the quality determination function from the plurality of fitting functions and the normalization coefficient.
With reference to the first aspect, an embodiment of the present invention provides a seventh possible implementation manner of the first aspect, where the selecting a face image whose quality score meets a preset condition includes:
and selecting one or more face images with the mass scores positioned in a preset interval.
In a second aspect, an embodiment of the present invention further provides a face recognition apparatus, including:
the receiving module is used for receiving a plurality of tracking images obtained by tracking and capturing the object to be identified;
the first determination module is used for determining a face image in each tracking image and a condition parameter value of the face image;
the second determining module is used for determining the quality score of the face image according to the condition parameter value and a preset quality determining function, wherein the quality determining function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image;
and the selecting module is used for selecting the face image with the quality score meeting the preset condition so as to be used for face recognition.
In a third aspect, an embodiment of the present invention further provides a face recognition system, where the face recognition system includes: an image sensor, a processor and a storage device;
the image sensor is used for tracking and capturing an object to be identified to obtain a plurality of tracking images;
the storage means has stored thereon a computer program which, when executed by the processor, performs the method according to the first aspect.
In a fourth aspect, the present invention also provides a computer-readable medium having non-volatile program code executable by a processor, where the program code causes the processor to execute the method of the first aspect.
The embodiment of the invention has the following beneficial effects: the embodiment of the invention firstly receives a plurality of tracking images obtained by tracking and capturing an object to be identified; then determining a face image in each tracking image and a condition parameter value of the face image; determining the quality score of the face image according to the condition parameter value and a preset quality determination function, wherein the quality determination function is determined according to the face recognition rate distribution corresponding to the condition parameter of the face image; and finally, selecting the face image with the quality score meeting the preset condition for face recognition.
The embodiment of the invention can determine the face image from a plurality of tracking images captured by tracking, and select the face image meeting the preset condition from the plurality of face images according to the quality scores of the face images, thereby reducing the operation amount of image recognition and shortening the image recognition time.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic block diagram of an electronic device provided by an embodiment of the invention;
fig. 2 is a flowchart of a face recognition method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an application scenario provided in the embodiment of the present invention;
fig. 4 is a schematic block diagram of a face recognition apparatus according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the present invention can be applied to an electronic device, and fig. 1 is a schematic block diagram of the electronic device according to the embodiment of the present invention. The electronic device shown in FIG. 1 includes one or more processors 102, one or more memory devices 104, an input device 106, an output device 108, an image sensor 110, and one or more non-image sensors 114, which are interconnected via a bus system 112 and/or otherwise. It should be noted that the components and configuration of the electronic device shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and configurations as desired.
The processor 102 may include a CPU1021 and a GPU1022 or other form of processing unit having data processing capability and/or Instruction execution capability, such as a Field-Programmable Gate Array (FPGA) or an Advanced Reduced Instruction Set Machine (Reduced Instruction Set Computer) Machine (ARM), etc., and the processor 102 may control other components in the electronic device to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory 1041 and/or non-volatile memory 1042. The volatile Memory 1041 may include, for example, a Random Access Memory (RAM), a cache Memory (cache), and/or the like. The non-volatile Memory 1042 may include, for example, a Read-Only Memory (ROM), a hard disk, a flash Memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium and executed by processor 102 to implement various desired functions. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 108 may output various information (e.g., images or sounds) to an external (e.g., user), and may include one or more of a display, a speaker, and the like.
The image sensor 110 may take images (e.g., photographs, videos, etc.) desired by the user and store the taken images in the storage device 104 for use by other components.
It should be noted that the components and structure of the electronic device shown in fig. 1 are only exemplary, and although the electronic device shown in fig. 1 includes a plurality of different devices, some of the devices may not be necessary, some of the devices may be more numerous, and the like, as required, and the present invention is not limited thereto.
Based on the fact that when a plurality of captured images are compared with a large number of images in a standard base one by one, the computation amount is very large, and the time required for image recognition is long, the face image can be determined in the plurality of captured images, the face image with the quality score meeting the preset conditions is selected from the plurality of face images, the computation amount of image recognition can be reduced, the image recognition time is shortened, and moreover, because the selected images are the tracked images meeting the preset conditions, the confidence coefficient of obtaining a correct recognition result can be improved, the accuracy rate of image recognition is improved, and the phenomena of missing recognition and error recognition are avoided.
To facilitate understanding of the present embodiment, a detailed description is first given of a face recognition method disclosed in the present embodiment, and as shown in fig. 2, the face recognition method may include the following steps.
Step S101, receiving a plurality of tracking images obtained by tracking and capturing an object to be identified.
In the embodiment of the present invention, the object to be recognized may refer to a pedestrian or the like. As an example, fig. 3 is a schematic view of an application scenario of an embodiment of the present invention, in fig. 3, during a process of passing through a door lock, as a pedestrian moves, an image sensor (e.g., a high-speed camera, etc.) may continuously Track and capture a face of the pedestrian along with the movement of the pedestrian to obtain a plurality of tracking images, this tracking and capturing process may be referred to as 1 Track (Track), and the number of the tracking images in 1 Track is Tack duration (seconds) × 25 (frames/second), and generally 10 to 70.
In addition, fig. 3 is a schematic view of only one scene of the present disclosure, the number and the detailed structure of the image sensors and the positions and the relative relationships between the image sensors and the object to be recognized are not limited in the drawing, and those skilled in the art can freely layout the positions and the relative relationships of the parts according to design or field requirements.
Step S102, determining a face image in each tracking image and a condition parameter value of the face image.
For example, a face image in the tracking image may be determined by using a face detection method, and a face frame containing a face may be determined by using a face detection algorithm. In an embodiment of the present invention, the condition parameter value may refer to a value of a condition parameter. The condition parameters may include: the method comprises the steps of obtaining a face image, wherein the face image comprises a fuzziness degree, a three-dimensional deflection angle of a face, a brightness of the face image or an area of the face image, wherein the three-dimensional deflection angle of the face can refer to a pitch angle (pitch), a yaw angle (yaw), a roll angle (roll) and the like of the face, and the condition parameter values can comprise a fuzziness value, a three-dimensional deflection angle value, a brightness value or an area value and the like.
And step S103, determining the quality score of the face image according to the condition parameter value and a preset quality determination function.
In the embodiment of the invention, the quality determination function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameters of the face image. For example, data curve fitting may be performed on the face recognition accuracy distribution corresponding to the condition parameter to obtain a fitting function, and/or data curve fitting may be performed on the confidence coefficient distribution corresponding to the condition parameter to obtain a fitting function, and then the quality determination function may be determined according to the fitting function.
For example, the recognition accuracy distribution corresponding to the condition parameter may refer to a distribution of recognition accuracy with respect to ambiguity, a distribution of recognition accuracy with respect to three-dimensional deflection angle, a distribution of recognition accuracy with respect to brightness, or a distribution of recognition accuracy with respect to an area of the target region, etc.; the confidence distribution corresponding to the condition parameter may refer to a distribution of confidence with respect to ambiguity, a distribution of confidence with respect to three-dimensional deflection angle, a distribution of confidence with respect to brightness, or a distribution of confidence with respect to an area of the target region, etc.
In this step, the conditional parameter values may be substituted into the quality determination function to obtain the quality score of the face image.
Illustratively, the step S103 may include the following steps.
1) And aiming at each of a plurality of facial images, respectively calculating the mass fraction component of the facial image according to the fitting function corresponding to each condition parameter.
Wherein the calculating the quality score components of the face image according to the fitting function corresponding to each condition parameter respectively comprises:
and respectively calculating the quality fraction components of the face images by using a fitting function determined according to the identification accuracy rate distribution corresponding to the condition parameters. Namely: assuming that the condition parameters of any face image are the blur degree and the brightness, when the mass fraction component is calculated, the fitting function determined according to the recognition accuracy distribution corresponding to the blur degree and the fitting function determined according to the recognition accuracy distribution corresponding to the brightness may be used.
Or respectively calculating the quality fraction components of the face images by using a fitting function determined according to the confidence coefficient distribution corresponding to the condition parameters. Namely: assuming that the condition parameters of any face image are the ambiguity and the brightness, when calculating the quality score component, the fitting function determined according to the confidence distribution corresponding to the ambiguity and the fitting function determined according to the confidence distribution corresponding to the brightness may be used.
Or calculating the quality score component of the face image by using a fitting function determined according to the recognition accuracy distribution corresponding to at least one condition parameter, and calculating the quality score component of the face image by using a fitting function determined according to the confidence coefficient distribution corresponding to other condition parameters. Namely: assuming that the condition parameters of any face image are the ambiguity and the brightness, when calculating the mass fraction component, a "fitting function determined according to the recognition accuracy distribution corresponding to the ambiguity" and a "fitting function determined according to the confidence distribution corresponding to the brightness" may be used.
That is, when calculating the mass fraction component of a certain face image, all the condition parameters may be calculated using a "fitting function determined according to the recognition accuracy distribution corresponding to the condition parameters", or all the condition parameters may be calculated using a "fitting function determined according to the confidence distribution corresponding to the condition parameters"; it is also possible to use "a fitting function determined from the recognition accuracy distribution corresponding to the condition parameter" for a part of the condition parameters, and "a fitting function determined from the confidence distribution corresponding to the condition parameter" for the remaining part of the condition parameters.
2) And carrying out normalization processing on the product of the quality fraction components of the face image to obtain the quality fraction.
Illustratively, in determining the quality score of a certain face image, it is assumed that only the ambiguity Blur and the three-dimensional deflection angle are considered. The product Q1 of the respective quality score components of the face image can be calculated with reference to the following formula.
Q1＝f1(Blur)*[f2a(Pitch)*f2b(Yaw)*f2c(Roll)]；
Where f1(Blur) indicates a mass fraction component with an ambiguity as an argument, Pitch indicates a Pitch angle, Yaw indicates a Yaw angle, and Roll indicates a Roll angle, f2a (Pitch) indicates a mass fraction component calculated with a Pitch angle as an argument, f2b (Yaw) indicates a mass fraction component calculated with a Yaw angle as an argument, and f2c (Roll) indicates a mass fraction component calculated with a Roll angle as an argument.
The product Q1 of the calculated quality score components may then be substituted into the quality determination function, resulting in a value that is the quality score of the face image.
The quality score Q may be calculated, for example, using the following quality determination function.
Q＝Q1*r+d；
Q1＝f1(x1)*f2(x2)*…*fn(xn)；
Where r and d are normalized coefficients, max (Q1) × r + d ═ 1; min (Q1) × r + d ═ 0; the independent variable xi is a condition parameter, and the cross correlation coefficient between any two xi is less than 0.1, i.e. the correlation degree between the xi is required to be extremely low, and fi (xi) can refer to a quality fraction component.
And step S104, selecting the face image with the quality score meeting the preset condition for face recognition.
The preset condition may refer to that the mass fraction is within a preset numerical range, or the like. Since the quality scores of the plurality of face images are calculated in step S103, one or more face images with quality scores within a preset numerical range can be selected from the plurality of face images. Furthermore, in practical application, the face recognition can be performed according to the selected face image.
The embodiment of the invention firstly receives a plurality of tracking images obtained by tracking and capturing an object to be identified; then determining a face image in each tracking image and a condition parameter value of the face image; (ii) a Determining the quality score of the face image according to the condition parameter value and a preset quality determination function, wherein the quality determination function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image; and finally, selecting the face image with the quality score meeting the preset condition for face recognition.
The embodiment of the invention can determine the face image in a plurality of images captured by tracking, and select the face image with the quality score meeting the preset condition from the plurality of face images, thereby reducing the operation amount of image recognition and shortening the image recognition time.
Optionally, before step S101, the method may further include the following step, and a fitting function determined according to the recognition accuracy distribution corresponding to the condition parameter may be obtained through the following step.
1) The identification accuracy distribution corresponding to each condition parameter can be respectively drawn according to historical image identification data, for example, assuming that the identification accuracy distribution is drawn, during drawing, the ambiguity can be used as an independent variable, the identification accuracy can be used as a dependent variable, the ambiguity can be used as an X axis, and the identification accuracy can be used as a Y axis to draw a distribution curve.
2) And respectively performing data curve fitting on the identification accuracy rate distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters of the face image and the identification accuracy rate distribution, wherein illustratively, a statistical tool of Matlab and the like can be used for performing data curve fitting.
Optionally, before step S101, the method may further include the following step, by which a fitting function determined according to the confidence distribution corresponding to the condition parameter may be obtained.
1) Respectively drawing confidence coefficient distribution corresponding to each condition parameter according to historical image identification data; for example, assuming that the distribution of the confidence with respect to the ambiguity is drawn, when drawing, the distribution curve may be drawn with the ambiguity as an independent variable, the confidence as a dependent variable, the ambiguity as an X-axis, and the confidence as a Y-axis.
2) And respectively performing data curve fitting on the confidence coefficient distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters and the confidence coefficient distribution of the face image, wherein, for example, a statistical tool of Matlab and the like can be used for performing data curve fitting.
Optionally, before step S101, the method may further comprise a step by which coefficients in the quality determination function, i.e. r and d as described in the previous embodiments, may be determined.
Multiplying the fitting functions corresponding to the plurality of condition parameters to obtain an intermediate function; determining a maximum value and a minimum value of the intermediate function; determining a normalization coefficient of the quality determination function according to the maximum value and the minimum value; determining the quality determination function from the plurality of fitting functions and the normalization coefficient.
In another embodiment of the present invention, as shown in fig. 4, there is also provided a face recognition apparatus, including: the device comprises a receiving module 11, a first determining module 12, a second determining module 13 and a selecting module 14;
the receiving module 11 is configured to receive a plurality of tracking images obtained by tracking and capturing an object to be identified;
a first determining module 12, configured to determine a face image in each of the tracking images and a condition parameter value of the face image;
a second determining module 13, configured to determine a quality score of the face image according to the condition parameter value and a preset quality determining function, where the quality determining function is determined according to face recognition accuracy distribution and/or confidence distribution corresponding to the condition parameter of the face image;
and the selecting module 14 is configured to select a face image with a quality score meeting a preset condition for face recognition.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
Optionally, the condition parameter includes at least one of: the blurring degree of the face image, the three-dimensional deflection angle of the face, the brightness of the face image and the area of the face image.
Optionally, the second determining module 13 may include: a computing unit and a processing unit;
the calculating unit is used for respectively calculating the quality fraction components of the face images according to the fitting function corresponding to each condition parameter aiming at each of a plurality of face images;
and the processing unit is used for carrying out normalization processing on the product of the quality fraction components of the face image to obtain the quality fraction.
Optionally, the computing unit may be configured to:
respectively calculating the mass fraction components of the face images by using a fitting function determined according to the identification accuracy rate distribution corresponding to the condition parameters;
or, respectively calculating the quality fraction components of the face images by using a fitting function determined according to the confidence coefficient distribution corresponding to the condition parameters;
or calculating the quality score component of the face image by using a fitting function determined according to the recognition accuracy distribution corresponding to at least one condition parameter, and calculating the quality score component of the face image by using a fitting function determined according to the confidence coefficient distribution corresponding to other condition parameters.
Optionally, the apparatus further comprises: a first rendering module and a first fitting module;
the first drawing module is used for respectively drawing the identification accuracy rate distribution corresponding to each condition parameter according to historical image identification data;
the first fitting module is used for respectively performing data curve fitting on the identification accuracy rate distribution corresponding to each condition parameter to obtain the fitting function determined according to the condition parameters of the face image and the identification accuracy rate distribution.
Optionally, the apparatus further comprises: a second rendering module and a second fitting module;
the second drawing module is used for respectively drawing confidence coefficient distribution corresponding to each condition parameter according to historical image identification data;
and the second fitting module is used for respectively performing data curve fitting on the confidence coefficient distribution corresponding to each condition parameter to obtain the fitting function determined according to the condition parameters and the confidence coefficient distribution of the face image.
Optionally, the apparatus further comprises: the device comprises a calculation module, a second determination module, a third determination module and a fourth determination module;
the calculation module is used for multiplying the fitting functions corresponding to the condition parameters to obtain an intermediate function;
the second determining module is used for determining the maximum value and the minimum value of the intermediate function;
the third determining module is configured to determine a normalization coefficient of the quality determination function according to the maximum value and the minimum value;
the fourth determining module is configured to determine the quality determining function according to the plurality of fitting functions and the normalization coefficient.
Optionally, the selecting module 13 may be configured to:
and selecting one or more face images with the mass scores positioned in a preset interval.
In another embodiment of the present invention, there is also provided a face recognition system, including: the device comprises an image acquisition device, a processor and a storage device;
the image acquisition device is used for the image sensor and is used for tracking and capturing an object to be identified to obtain a plurality of tracking images;
the storage means has stored thereon a computer program which, when executed by the processor, performs the method according to the preceding method embodiment.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
In a further embodiment of the invention, a computer-readable medium is also provided having non-volatile program code executable by a processor, the program code causing the processor to perform the method as described in the aforementioned method embodiments.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The face recognition method, the face recognition device and the computer program product of the system provided by the embodiment of the invention comprise a computer readable storage medium storing a program code, wherein instructions included in the program code can be used for executing the method described in the foregoing method embodiment, and specific implementation can refer to the method embodiment, which is not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A face recognition method, comprising:
receiving a plurality of tracking images obtained by tracking and capturing an object to be identified;
determining a face image in each tracking image and a condition parameter value of the face image; the condition parameter includes at least one of: the method comprises the following steps of (1) blurring degree of a face image, three-dimensional deflection angle of a face, brightness of the face image and area of the face image;
determining the quality score of the face image according to the condition parameter value and a preset quality determination function, wherein the quality determination function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image; the quality determination function is determined in the following manner: performing data curve fitting on the face recognition accuracy rate distribution corresponding to the condition parameters to obtain a fitting function, and/or performing data curve fitting on the confidence coefficient distribution corresponding to the condition parameters to obtain a fitting function, and determining a quality determination function according to the fitting function;
and selecting the face image with the quality score meeting the preset condition for face recognition.
2. The method for recognizing the human face according to the claim 1, wherein the determining the quality score of the human face image according to the condition parameter value and a preset quality determination function comprises:
aiming at each of a plurality of face images, respectively calculating the mass fraction component of the face image according to the fitting function corresponding to each condition parameter;
and carrying out normalization processing on the product of the quality fraction components of the face image to obtain the quality fraction.
3. The method according to claim 2, wherein the calculating the quality score components of the face image according to the fitting function corresponding to each of the condition parameters comprises:
respectively calculating the mass fraction components of the face images by using a fitting function determined according to the identification accuracy rate distribution corresponding to the condition parameters;
or, respectively calculating the quality fraction components of the face images by using a fitting function determined according to the confidence coefficient distribution corresponding to the condition parameters;
or calculating the quality score component of the face image by using a fitting function determined according to the recognition accuracy distribution corresponding to at least one condition parameter, and calculating the quality score component of the face image by using a fitting function determined according to the confidence coefficient distribution corresponding to other condition parameters.
4. The method of claim 3, further comprising:
respectively drawing identification accuracy rate distribution corresponding to each condition parameter according to historical image identification data;
and respectively carrying out data curve fitting on the identification accuracy rate distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters of the face image and the identification accuracy rate distribution.
5. The method of claim 3, further comprising:
respectively drawing confidence coefficient distribution corresponding to each condition parameter according to historical image identification data;
and respectively carrying out data curve fitting on the confidence coefficient distribution corresponding to each condition parameter to obtain a fitting function determined according to the condition parameters and the confidence coefficient distribution of the face image.
6. The face recognition method of claim 4 or 5, wherein the method further comprises:
multiplying the fitting functions corresponding to the plurality of condition parameters to obtain an intermediate function;
determining a maximum value and a minimum value of the intermediate function;
determining a normalization coefficient of the quality determination function according to the maximum value and the minimum value;
determining the quality determination function from the plurality of fitting functions and the normalization coefficient.
7. The face recognition method of claim 6, wherein the selecting the face image with the quality score meeting the preset condition comprises:
and selecting one or more face images with the mass scores positioned in a preset interval.
8. A face recognition apparatus, comprising:
the receiving module is used for receiving a plurality of tracking images obtained by tracking and capturing the object to be identified;
the first determination module is used for determining a face image in each tracking image and a condition parameter value of the face image; the condition parameter includes at least one of: the method comprises the following steps of (1) blurring degree of a face image, three-dimensional deflection angle of a face, brightness of the face image and area of the face image;
the second determining module is used for determining the quality score of the face image according to the condition parameter value and a preset quality determining function, wherein the quality determining function is determined according to face recognition accuracy rate distribution and/or confidence coefficient distribution corresponding to the condition parameter of the face image; the quality determination function is determined in the following manner: performing data curve fitting on the face recognition accuracy rate distribution corresponding to the condition parameters to obtain a fitting function, and/or performing data curve fitting on the confidence coefficient distribution corresponding to the condition parameters to obtain a fitting function, and determining a quality determination function according to the fitting function;
and the selecting module is used for selecting the face image with the quality score meeting the preset condition so as to be used for face recognition.
9. A face recognition system, the system comprising: an image sensor, a processor and a storage device;
the image sensor is used for tracking and capturing an object to be identified to obtain a plurality of tracking images;
the storage device has stored thereon a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710700742.9A CN108876758B (en) | 2017-08-15 | 2017-08-15 | Face recognition method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710700742.9A CN108876758B (en) | 2017-08-15 | 2017-08-15 | Face recognition method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108876758A CN108876758A (en) | 2018-11-23 |
| CN108876758B true CN108876758B (en) | 2020-11-24 |
Family
ID=64325424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710700742.9A Active CN108876758B (en) | 2017-08-15 | 2017-08-15 | Face recognition method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876758B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369521A (en) * | 2020-03-02 | 2020-07-03 | 名创优品（横琴）企业管理有限公司 | Image filtering method based on image quality and related device |
| CN115002414A (en) * | 2020-03-20 | 2022-09-02 | 腾讯云计算（北京）有限责任公司 | Monitoring method, monitoring device, server and computer readable storage medium |
| CN112257638A (en) * | 2020-10-30 | 2021-01-22 | 重庆紫光华山智安科技有限公司 | Image comparison method, system, equipment and computer readable storage medium |
| CN112766239A (en) * | 2021-03-15 | 2021-05-07 | 中国工商银行股份有限公司 | Face recognition method, face recognition system, electronic equipment and storage medium |
| CN113283305B (en) * | 2021-04-29 | 2024-03-26 | 百度在线网络技术（北京）有限公司 | Face recognition method, device, electronic equipment and computer readable storage medium |
| CN113255608B (en) * | 2021-07-01 | 2021-11-19 | 杭州智爱时刻科技有限公司 | Multi-camera face recognition positioning method based on CNN classification |
| CN113763348A (en) * | 2021-09-02 | 2021-12-07 | 北京格灵深瞳信息技术股份有限公司 | Image quality determination method and device, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7693304B2 (en) * | 2005-05-12 | 2010-04-06 | Hewlett-Packard Development Company, L.P. | Method and system for image quality calculation |
| CN101567044B (en) * | 2009-05-22 | 2012-08-22 | 北京大学 | Method for detecting quality of human face image |
| CN105046245B (en) * | 2015-08-28 | 2018-08-03 | 深圳英飞拓科技股份有限公司 | Video human face method of determination and evaluation |
| CN105472239B (en) * | 2015-11-17 | 2019-08-16 | 小米科技有限责任公司 | Photo processing method and device |
| CN105608700B (en) * | 2015-12-24 | 2019-12-17 | 广州视源电子科技股份有限公司 | Photo screening method and system |
| CN105631439B (en) * | 2016-02-18 | 2019-11-08 | 北京旷视科技有限公司 | Face image processing process and device |
-
2017
- 2017-08-15 CN CN201710700742.9A patent/CN108876758B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108876758A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876758B (en) | Face recognition method, device and system | |
| CN109711304B (en) | Face feature point positioning method and device | |
| CN108492287B (en) | Video jitter detection method, terminal equipment and storage medium | |
| KR20200015728A (en) | Target object recognition method, apparatus, storage medium and electronic device | |
| CN111798487B (en) | Target tracking method, apparatus and computer readable storage medium | |
| JP4575829B2 (en) | Display screen position analysis device and display screen position analysis program | |
| JP5925068B2 (en) | Video processing apparatus, video processing method, and program | |
| EP3477593B1 (en) | Hand detection and tracking method and device | |
| US20150104067A1 (en) | Method and apparatus for tracking object, and method for selecting tracking feature | |
| KR102474837B1 (en) | Foreground area extracting method and apparatus | |
| CN107784281B (en) | Method for detecting human face, device, equipment and computer-readable medium | |
| CN108921070B (en) | Image processing method, model training method and corresponding device | |
| CN112016371A (en) | Face key point detection method, device, equipment and storage medium | |
| CN107993256A (en) | Dynamic target tracking method, apparatus and storage medium | |
| CN110738078A (en) | face recognition method and terminal equipment | |
| CN112966654B (en) | Lip movement detection method, lip movement detection device, terminal equipment and computer readable storage medium | |
| CN110298237B (en) | Head gesture recognition method, head gesture recognition device, computer equipment and storage medium | |
| EP3109695B1 (en) | Method and electronic device for automatically focusing on moving object | |
| CN112418153B (en) | Image processing method, device, electronic equipment and computer storage medium | |
| CN111382606A (en) | Tumble detection method, tumble detection device and electronic equipment | |
| JP6798609B2 (en) | Video analysis device, video analysis method and program | |
| JP2016170603A (en) | Moving body tracking device | |
| US20130265420A1 (en) | Video processing apparatus, video processing method, and recording medium | |
| KR20090115738A (en) | Information extracting method, registering device, collating device and program | |
| CN113158706B (en) | Face snapshot method, device, medium and electronic equipment |
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 |