CN113177466A - Identity recognition method and device based on face image, electronic equipment and medium - Google Patents
Identity recognition method and device based on face image, electronic equipment and medium Download PDFInfo
- Publication number
- CN113177466A CN113177466A CN202110460563.9A CN202110460563A CN113177466A CN 113177466 A CN113177466 A CN 113177466A CN 202110460563 A CN202110460563 A CN 202110460563A CN 113177466 A CN113177466 A CN 113177466A
- Authority
- CN
- China
- Prior art keywords
- face image
- base
- texture
- information
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
Abstract
The present disclosure provides an identity recognition method, device, electronic device and medium based on a face image, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as computer vision, deep learning, augmented reality, and the like. The specific implementation scheme is as follows: acquiring an initial face image; processing the initial face image to obtain corresponding base information; carrying out image compression processing on the initial face image according to the substrate information to obtain a face image to be recognized; and determining confidence information according to the base information and the face image to be recognized, wherein the confidence information is used for identity recognition. Because the human face image to be recognized obtained by compression processing is used for identity recognition, the image acquisition and transmission efficiency can be effectively improved in the identity recognition process, the calculated amount in the identity recognition process is effectively reduced, the identity recognition efficiency is improved, and the identity recognition effect is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to the field of artificial intelligence technologies such as computer vision, deep learning, and augmented reality, and in particular, to a method and an apparatus for identity recognition based on a face image, an electronic device, and a medium.
Background
Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.
The adoption of face images for user identification is a hot research field.
Disclosure of Invention
The present disclosure provides a face image-based identity recognition method, apparatus, electronic device, storage medium, and computer program product.
According to a first aspect of the present disclosure, there is provided an identity recognition method based on a face image, including: acquiring an initial face image; processing the initial face image to obtain corresponding base information; performing image compression processing on the initial face image according to the base information to obtain a face image to be recognized; and determining confidence information according to the base information and the face image to be recognized, wherein the confidence information is used for identity recognition.
According to a second aspect of the present disclosure, there is provided an identity recognition apparatus based on a face image, comprising: the acquisition module is used for acquiring an initial face image; the first processing module is used for processing the initial face image to obtain corresponding base information; the second processing module is used for carrying out image compression processing on the initial face image according to the base information so as to obtain a face image to be recognized; and the determining module is used for determining confidence coefficient information according to the base information and the face image to be recognized, and the confidence coefficient information is used for identity recognition.
According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for identification based on facial images of the disclosed embodiments.
According to a fourth aspect, a non-transitory computer-readable storage medium is provided, in which computer instructions are stored, the computer instructions being configured to cause the computer to perform the method for identifying an identity based on a face image disclosed in the embodiments of the present disclosure.
According to a fifth aspect, a computer program product is proposed, which comprises a computer program that, when executed by a processor, implements the facial image-based identity recognition method disclosed in the embodiments of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device for implementing the identity recognition method based on a face image according to the embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure.
It should be noted that an execution subject of the identity recognition method based on a face image in this embodiment is an identity recognition device based on a face image, the device may be implemented in a software and/or hardware manner, the device may be configured in an electronic device, and the electronic device may include but is not limited to a terminal, a server, and the like.
The embodiment of the disclosure relates to the technical field of artificial intelligence such as computer vision, deep learning and augmented reality.
Wherein, Artificial Intelligence (Artificial Intelligence), english is abbreviated as AI. The method is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
Deep learning is the intrinsic law and expression level of the learning sample data, and the information obtained in the learning process is very helpful for the interpretation of data such as characters, images and sounds. The final goal of deep learning is to make a machine capable of human-like analytical learning, and to recognize data such as characters, images, and sounds.
Augmented Reality (AR) technology is a technology that skillfully fuses virtual information and the real world, and a plurality of technical means such as multimedia, three-dimensional modeling, real-time tracking and registration, intelligent interaction, sensing and the like are widely applied, and virtual information such as characters, images, three-dimensional models, music, videos and the like generated by a computer is applied to the real world after analog simulation, and the two kinds of information complement each other, so that the real world is enhanced.
Computer vision means that a camera and a computer are used to replace human eyes to perform machine vision such as identification, tracking and measurement on a target, and further image processing is performed, so that the computer processing becomes an image more suitable for human eye observation or transmitted to an instrument for detection.
As shown in fig. 1, the identity recognition method based on the face image includes:
s101: and acquiring an initial face image.
The face image initially acquired may be referred to as an initial face image, and the initial face image may include a face region therein.
The embodiment of the disclosure may be applied to a process of identifying an identity of a user by using an electronic device, for example, to identify whether the user a is an authorized user of the electronic device, and in the process of identifying the identity, a camera of the electronic device may be turned on, and then an image including a face area of the user a is captured based on the camera and is used as an initial face image, or a plurality of video frames of a scene where the electronic device is located may also be captured, and then an image including the face area of the user a is obtained by parsing from the plurality of video frames and is used as the initial face image, which is not limited.
It should be noted that the initial face image obtained in this step includes face information of the user, but the obtaining process of the initial face image is executed after being authorized by the user, and the obtaining process conforms to relevant laws and regulations.
S102: and processing the initial face image to obtain corresponding base information.
After the initial face image is obtained, the initial face image may be processed to obtain corresponding base information.
The information describing the base component of the face may be referred to as base information, and the base component of the face may be, for example, a texture, a contour, and the like of the face itself, and correspondingly, the base information may include one or more texture base components, such as a texture, a contour, and the like of the face itself, and the base information is not limited thereto.
In the embodiment of the disclosure, after an initial face image is obtained, the initial face image may be subjected to component division by a principal component analysis method to obtain one or more texture base components included in the initial face image, and the one or more texture base components are used as base information corresponding to the initial face image, and then subsequent steps are triggered.
S103: and carrying out image compression processing on the initial face image according to the base information to obtain a face image to be recognized.
After the initial face image is obtained and processed to obtain the corresponding base information, the initial face image may be subjected to image compression processing with reference to the base information to obtain a face image to be recognized.
That is to say, the information and the like related to the texture, the contour and the like of the face itself extracted from the initial face image can be adopted to assist in performing image compression processing on the initial face image, so as to obtain a compressed face image and use the compressed face image as a face image to be recognized, and the face image to be recognized can be used for identity recognition in the following process.
The image compression processing is assisted to the initial face image by referring to the texture, contour and other related information of the face during compression, so that the image acquisition and transmission efficiency is effectively improved in the identity recognition process, the calculated amount in the identity recognition process is effectively reduced, the compressed face image to be recognized still carries important characteristic information required by identity recognition, and the accuracy of subsequent recognition is guaranteed.
Optionally, in some embodiments, the image compression processing is performed on the initial face image according to the basis information to obtain the face image to be recognized, and may be that a texture basis coefficient matrix is determined according to the basis information, where the texture basis coefficient matrix includes: a plurality of basis coefficients, which are weight coefficients of texture basis components contained in the basis information with respect to standard basis components; the initial face image is subjected to image compression processing according to the texture base coefficient matrix to obtain a face image to be recognized, and the initial face image is subjected to image compression processing by referring to the weight coefficient of a texture base component relative to a standard base component contained in the base information, so that important feature information contained in the initial face image can be effectively retained, the complexity of compression processing is reduced, and the efficiency of the whole identity recognition process is effectively improved while the identity recognition accuracy is guaranteed.
That is, after one or more texture base components included in the initial face image are obtained through analysis, each texture base component may be compared with a corresponding standard base component, a proportionality coefficient between each texture base component and the corresponding standard base component is determined, the proportionality coefficient is used as a base coefficient, and then a texture base coefficient matrix is formed according to a plurality of base coefficients, so that the initial face image is subjected to image compression processing by using the texture base coefficient matrix.
In some embodiments, when the texture basis coefficient matrix is used to perform image compression processing on the initial face image, the texture basis coefficient matrix may be used to input the initial face image into a pre-trained compression model, and obtain a compressed face image output by the compression model and use the compressed face image as a face image to be recognized, or any other possible manner may be used to perform image compression processing on the initial face image by using the texture basis coefficient matrix, which is not limited to this.
S104: and determining confidence information according to the base information and the face image to be recognized, wherein the confidence information is used for identity recognition.
After the initial face image is subjected to image compression processing by adopting the texture basis coefficient matrix to obtain the face image to be recognized, identity recognition can be carried out directly on the basis of the face image to be recognized in an auxiliary mode.
In the embodiment of the present disclosure, the confidence information corresponding to the face image to be recognized may be determined by combining the base information obtained by the analysis and the face image to be recognized, and the confidence information may represent a credibility that a face region included in the face image to be recognized belongs to an authorized user of the electronic device, so as to assist in performing rapid and efficient identity recognition.
In the embodiment, the initial face image is obtained and processed to obtain the corresponding base information, the initial face image is subjected to image compression processing according to the base information to obtain the face image to be recognized, and the confidence information is determined according to the base information and the face image to be recognized, and is used for identity recognition.
Fig. 2 is a schematic diagram according to a second embodiment of the present disclosure.
As shown in fig. 2, the identity recognition method based on the face image includes:
s201: and acquiring an initial face image.
S202: and processing the initial face image to obtain corresponding base information.
For the description of S201-S202, reference may be made to the above embodiments, which are not described herein again.
S203: and determining a plurality of standard substrate components respectively corresponding to the plurality of texture substrate components in the substrate information by adopting a pre-trained regression model.
After the initial face image is subjected to component division through a principal component analysis method to obtain one or more texture base components included in the initial face image and the one or more texture base components are used as base information corresponding to the initial face image, a pre-trained regression model can be adopted to determine a plurality of standard base components respectively corresponding to the plurality of texture base components in the base information.
It can be understood that, since the base information of different human faces can be obtained by the texture base component which is arbitrarily combined, in the embodiment of the present disclosure, a linear model based on the human face texture base can be pre-constructed, then, the human face image of the sample is subjected to gaussian distribution fitting by using the principal component analysis method to obtain a parameterized human face model, and the human face image of the sample is decomposed into the standard base component T of the human face texturex＝a1T1+a2T2+a3T3+......+anTnWhile reducing the dimension of the variable, thereby T therein1、T2、T3、…、TnBoth may be referred to as standard base compositions.
In the embodiment of the present disclosure, the plurality of standard base components respectively corresponding to the plurality of texture base components in the base information may be part of the labeling base components in the plurality of standard base components in the linear model based on the human face texture base.
The standard base component T is used for decomposing the face image of the sample into the human face texturex＝a1T1+a2T2+a3T3+......+anTnThen, the sample base information T of the face image of the sample in the face texture library can be obtainedyWith a standard base composition TxEstablishing a polynomial nonlinear relation, and then training the linear model based on the human face texture substrate by adopting the polynomial nonlinear relation to obtain a polynomial regression model T ═ (a ═1T1)n+(a2T2)n+(a3T3)n+......+(anTn)nThe polynomial regression model T ═ a1T1)n+(a2T2)n+(a3T3)n+......+(anTn)nI.e. may be referred to as the above-mentioned pre-trained regression model.
Correspondingly, a pre-trained regression model is adopted to determine a plurality of standard substrate components respectively corresponding to a plurality of texture substrate components in the substrate information, and then the subsequent steps are triggered.
S204: a plurality of weighting coefficients for a plurality of texture base components relative to corresponding standard base components are determined.
After determining the plurality of standard base components respectively corresponding to the plurality of texture base components in the base information by using the pre-trained regression model, a plurality of weighting coefficients of the plurality of texture base components relative to the corresponding standard base components may be determined.
Weighting factors such as a1、a2、a3，…，anAnd the various texture base components may be, for example, T as described above1、T2、T3，…，TnThis is not limitative.
S205: and generating a texture base coefficient matrix according to the multiple weight coefficients.
After the pre-trained regression model is adopted to determine the plurality of standard substrate components respectively corresponding to the plurality of texture substrate components in the substrate information, the plurality of weighting coefficients of the plurality of texture substrate components relative to the corresponding standard substrate components can be determined, and then the texture substrate coefficient matrix can be generated according to the plurality of weighting coefficients.
That is, the corresponding texture base coefficient matrix can be obtained according to the combination of various weighting coefficients.
The method comprises the steps of determining a plurality of standard substrate components corresponding to a plurality of texture substrate components in substrate information respectively by adopting a pre-trained regression model, determining a plurality of weight coefficients of the plurality of texture substrate components relative to the corresponding standard substrate components, and generating a texture substrate coefficient matrix according to the plurality of weight coefficients, so that the weight coefficients of the texture substrate components contained in the substrate information relative to the standard substrate components can be rapidly and accurately determined, the resolution efficiency of the weight coefficients is improved, the identification efficiency is ensured based on a plurality of dimensions, the resolution accuracy of the weight coefficients is also ensured, and the accuracy and the identification effect of identification are effectively assisted to be improved.
S206: and generating a face texture image corresponding to the initial face image according to the plurality of basis coefficients and the plurality of standard basis components, and taking the face texture image as the face image to be recognized.
After the corresponding texture base coefficient matrix is obtained according to the combination of the multiple weight coefficients, the face texture image corresponding to the initial face image can be generated directly according to the multiple base coefficients and the multiple standard base components, and the face texture image is used as the face image to be recognized, so that the face image is compressed by adopting the extracted texture base coefficient matrix, and high-efficiency image data processing and transmission are completed.
In some embodiments, for example, an image synthesis method may be used to perform texture image synthesis on the multiple base coefficients and the corresponding multiple standard base components, so as to obtain a face texture image, or any other possible manner may be used to synthesize the multiple base coefficients and the multiple standard base components, which is not limited herein.
For example, after an initial face image is obtained, a principal component analysis method may be used to perform component division on the initial face image to obtain basis information, then basis coefficients between the basis information of the initial face image and various standard basis components are calculated through a pre-trained regression model to obtain a texture basis coefficient matrix, then a plurality of basis coefficients in the texture basis coefficient matrix and various standard basis components may be synthesized to obtain a face texture image corresponding to the initial face image, and the face texture image includes: texture features corresponding to the original face image.
S207: a plurality of first weights corresponding to the plurality of texture base components, respectively, are determined.
After the face texture image corresponding to the initial face image is generated according to the plurality of basis coefficients and the plurality of standard basis components, the face texture image can be directly used as a face image to be recognized, namely, identity recognition is assisted based on the face image to be recognized.
For example, confidence information may be determined based on the facial image to be recognized, and the confidence information may represent a confidence level that a facial region included in the facial image to be recognized belongs to an authorized user of the electronic device, thereby facilitating rapid and efficient identity recognition.
In the embodiment of the present disclosure, a plurality of first weights respectively corresponding to a plurality of texture base components may be determined, where the first weights may be used to represent the degree of action of the corresponding texture base components on identification, and the texture base components with higher weights have higher degrees of action on identification.
The first weight may be previously calibrated for the standard base component, so that the weight corresponding to the standard base component may be directly used as the first weight corresponding to the texture base component.
S208: and determining a candidate face image corresponding to the face image to be recognized, and determining a plurality of second weights respectively corresponding to a plurality of standard substrate components in the candidate face image.
After determining the plurality of first weights respectively corresponding to the plurality of texture basis components, the candidate face image corresponding to the face image to be recognized can be determined, and a plurality of second weights respectively corresponding to the plurality of standard basis components in the candidate face image can be determined.
The candidate face image can be a standard face image in an image library, the similarity of the candidate face image and the face image to be recognized meets a certain condition, the standard face image can also be a texture image of a standard face, and then a plurality of weights respectively corresponding to a plurality of standard base components in the candidate face image are used as second weights.
Wherein the second weight can be used to represent the degree of contribution of the corresponding standard base component to identification, and the texture base component with higher weight has larger degree of contribution to identification.
The second weight may be calibrated in advance for the standard base component, so that a plurality of second weights respectively corresponding to a plurality of standard base components in the candidate face image may be directly determined.
S209: and determining confidence coefficient information according to the plurality of first weights and the plurality of second weights, wherein the confidence coefficient information is used for identity recognition.
After determining the plurality of first weights respectively corresponding to the plurality of texture basis components and determining the plurality of second weights respectively corresponding to the plurality of standard basis components in the candidate face image, the texture similarity between the face image to be recognized and the candidate face image may be determined according to the plurality of first weights and the plurality of second weights, and the texture similarity is used as the confidence information, which is not limited herein.
The confidence information is determined according to the multiple first weights and the multiple second weights, so that the confidence information is calculated by referring to the weights of the various texture base components, the referential property of the confidence information is effectively improved, the false recognition is effectively avoided, and the accuracy of the identity recognition is improved.
Optionally, in some embodiments, the confidence information is determined according to the plurality of first weights and the plurality of second weights, which may be determining euclidean distances between the plurality of first weights and the corresponding plurality of second weights, and using the euclidean distances as the confidence information, so that the method is simple and convenient to implement, has high operation accuracy, and effectively reduces software and hardware resources consumed by operation.
For example, the weights of the standard base components in the standard face image in the face texture library can be preset, then, the first weights corresponding to the various texture base components in the face image to be recognized and the texture base component parameters jointly form texture feature information corresponding to the face image to be recognized, the confidence information of the image to be recognized can be obtained by dividing the texture base components of the face image to be recognized, then, the first weights corresponding to the texture base components and a plurality of second weights corresponding to a plurality of standard base components in the candidate face image in the comparison library respectively, and identity recognition is carried out based on the preset confidence threshold.
Therefore, the embodiment of the disclosure can realize quantization processing of texture basis components in a face image to be recognized, and realize fast acquisition of a texture basis coefficient matrix for assisting in processing and compressing an initial face image by establishing a regression model, thereby improving transmission efficiency.
In the embodiment, the initial face image is obtained and processed to obtain the corresponding base information, the initial face image is subjected to image compression processing according to the base information to obtain the face image to be recognized, and the confidence information is determined according to the base information and the face image to be recognized, and is used for identity recognition. The method comprises the steps of determining a plurality of standard substrate components corresponding to a plurality of texture substrate components in substrate information respectively by adopting a pre-trained regression model, determining a plurality of weight coefficients of the plurality of texture substrate components relative to the corresponding standard substrate components, and generating a texture substrate coefficient matrix according to the plurality of weight coefficients, so that the weight coefficients of the texture substrate components contained in the substrate information relative to the standard substrate components can be rapidly and accurately determined, the resolution efficiency of the weight coefficients is improved, the identification efficiency is ensured based on a plurality of dimensions, the resolution accuracy of the weight coefficients is also ensured, and the accuracy and the identification effect of identification are effectively assisted to be improved. The confidence information is determined according to the multiple first weights and the multiple second weights, so that the confidence information is calculated by referring to the weights of the various texture base components, the referential property of the confidence information is effectively improved, the false recognition is effectively avoided, and the accuracy of the identity recognition is improved.
Fig. 3 is a schematic diagram according to a third embodiment of the present disclosure.
As shown in fig. 3, the identification apparatus 30 based on human face image includes:
an obtaining module 301, configured to obtain an initial face image.
The first processing module 302 is configured to process the initial face image to obtain corresponding base information.
And the second processing module 303 is configured to perform image compression processing on the initial face image according to the base information to obtain a face image to be recognized.
And the determining module 304 is configured to determine confidence information according to the basis information and the face image to be recognized, where the confidence information is used for identity recognition.
In some embodiments of the present disclosure, as shown in fig. 4, fig. 4 is a schematic diagram of an identity recognition apparatus 40 based on a face image according to a fourth embodiment of the present disclosure, including: the device comprises an obtaining module 401, a first processing module 402, a second processing module 403, and a determining module 404, wherein the second processing module 403 includes:
a determining submodule 4031, configured to determine a texture base coefficient matrix according to the base information, where the texture base coefficient matrix includes: the plurality of basis coefficients are weighting coefficients of texture basis components contained in the basis information with respect to the standard basis components.
And the processing submodule 4032 is configured to perform image compression processing on the initial face image according to the texture basis coefficient matrix to obtain a face image to be recognized.
In some embodiments of the present disclosure, the determining sub-module 4031 is specifically configured to:
determining a plurality of standard substrate components respectively corresponding to a plurality of texture substrate components in the substrate information by adopting a pre-trained regression model;
determining a plurality of weighting coefficients of a plurality of texture base components relative to corresponding standard base components;
and generating a texture base coefficient matrix according to the multiple weight coefficients.
In some embodiments of the present disclosure, the processing sub-module 4032 is specifically configured to:
and generating a face texture image corresponding to the initial face image according to the plurality of basis coefficients and the plurality of standard basis components, and taking the face texture image as the face image to be recognized.
In some embodiments of the present disclosure, the determining module 404 is specifically configured to:
determining a plurality of first weights respectively corresponding to the plurality of texture base components;
determining a candidate face image corresponding to the face image to be recognized, and determining a plurality of second weights respectively corresponding to a plurality of standard substrate components in the candidate face image;
confidence information is determined according to the plurality of first weights and the plurality of second weights.
In some embodiments of the present disclosure, the determining module 404 is specifically configured to:
and determining Euclidean distances between the plurality of first weights and the corresponding plurality of second weights, and taking the Euclidean distances as confidence degree information.
It is understood that the facial image-based identification device 40 in fig. 4 of the present embodiment and the facial image-based identification device 30 in the above-mentioned embodiment, the acquiring module 401 and the acquiring module 301 in the above-mentioned embodiment, the first processing module 402 and the first processing module 302 in the above-mentioned embodiment, the second processing module 403 and the second processing module 303 in the above-mentioned embodiment, and the determining module 404 and the determining module 304 in the above-mentioned embodiment may have the same functions and structures.
It should be noted that the foregoing explanation of the identification method based on a face image is also applicable to the identification apparatus based on a face image in this embodiment, and is not repeated herein.
In the embodiment, the initial face image is obtained and processed to obtain the corresponding base information, the initial face image is subjected to image compression processing according to the base information to obtain the face image to be recognized, and the confidence information is determined according to the base information and the face image to be recognized, and is used for identity recognition.
It should be noted that the face image in the embodiment of the present application is not a face image for a specific user, and cannot reflect personal information of a specific user.
The face image in the embodiment of the application may be from a public data set, or the face image is obtained by authorization of a user corresponding to the face image.
In the embodiment of the application, the executing subject of the identity recognition method based on the face image may obtain the face image in various public and legal compliance manners, for example, the face image may be obtained from a public data set, or obtained from a user after authorization of the user.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
Fig. 5 is a block diagram of an electronic device for implementing the identity recognition method based on a face image according to the embodiment of the present disclosure.
Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM502, and the RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 performs the respective methods and processes described above, for example, a face image-based identification method.
For example, in some embodiments, the facial image-based identification method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM502 and/or the communication unit 509. When the computer program is loaded into the RAM503 and executed by the computing unit 501, one or more steps of the above described face image based identification method may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the face image-based identification method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the facial image-based identification method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. An identity recognition method based on face images comprises the following steps:
acquiring an initial face image;
processing the initial face image to obtain corresponding base information;
performing image compression processing on the initial face image according to the base information to obtain a face image to be recognized; and
and determining confidence information according to the base information and the face image to be recognized, wherein the confidence information is used for identity recognition.
2. The method of claim 1, wherein the image compression processing on the initial face image according to the base information to obtain a face image to be recognized comprises:
determining a texture base coefficient matrix according to the base information, wherein the texture base coefficient matrix comprises: a plurality of base coefficients that are weighting coefficients of texture base components contained in the base information with respect to standard base components;
and carrying out image compression processing on the initial face image according to the texture base coefficient matrix to obtain a face image to be recognized.
3. The method of claim 2, wherein the determining a texture base coefficient matrix from the base information comprises:
determining a plurality of standard substrate components respectively corresponding to a plurality of texture substrate components in the substrate information by adopting the pre-trained regression model;
determining a plurality of weighting coefficients for the plurality of texture base components relative to corresponding standard base components;
and generating the texture base coefficient matrix according to the multiple weight coefficients.
4. The method according to claim 3, wherein the image compression processing on the initial face image according to the texture base coefficient matrix to obtain a face image to be recognized comprises:
and generating a face texture image corresponding to the initial face image according to the plurality of basis coefficients and the plurality of standard basis components, and taking the face texture image as the face image to be recognized.
5. The method of claim 3, wherein determining confidence information from the basis information and the facial image to be recognized comprises:
determining a plurality of first weights respectively corresponding to the plurality of texture base components;
determining a candidate face image corresponding to the face image to be recognized, and determining a plurality of second weights respectively corresponding to a plurality of standard substrate components in the candidate face image;
determining the confidence information according to the plurality of first weights and the plurality of second weights.
6. The method of claim 5, wherein said determining the confidence information based on the plurality of first weights and the plurality of second weights comprises:
determining Euclidean distances between the plurality of first weights and the corresponding plurality of second weights, and using the Euclidean distances as the confidence degree information.
7. An identity recognition device based on face image comprises
The acquisition module is used for acquiring an initial face image;
the first processing module is used for processing the initial face image to obtain corresponding base information;
the second processing module is used for carrying out image compression processing on the initial face image according to the base information so as to obtain a face image to be recognized; and
and the determining module is used for determining confidence coefficient information according to the base information and the face image to be recognized, wherein the confidence coefficient information is used for identity recognition.
8. The apparatus of claim 7, wherein the second processing module comprises:
a determining submodule, configured to determine a texture base coefficient matrix according to the base information, where the texture base coefficient matrix includes: a plurality of base coefficients that are weighting coefficients of texture base components contained in the base information with respect to standard base components;
and the processing submodule is used for carrying out image compression processing on the initial face image according to the texture basis coefficient matrix so as to obtain a face image to be recognized.
9. The apparatus according to claim 8, wherein the determining submodule is specifically configured to:
determining a plurality of standard substrate components respectively corresponding to a plurality of texture substrate components in the substrate information by adopting the pre-trained regression model;
determining a plurality of weighting coefficients for the plurality of texture base components relative to corresponding standard base components;
and generating the texture base coefficient matrix according to the multiple weight coefficients.
10. The apparatus of claim 8, wherein the processing submodule is specifically configured to:
and generating a face texture image corresponding to the initial face image according to the plurality of basis coefficients and the plurality of standard basis components, and taking the face texture image as the face image to be recognized.
11. The apparatus of claim 9, wherein the determining module is specifically configured to:
determining a plurality of first weights respectively corresponding to the plurality of texture base components;
determining a candidate face image corresponding to the face image to be recognized, and determining a plurality of second weights respectively corresponding to a plurality of standard substrate components in the candidate face image;
determining the confidence information according to the plurality of first weights and the plurality of second weights.
12. The apparatus of claim 11, wherein the determining module is specifically configured to:
determining Euclidean distances between the plurality of first weights and the corresponding plurality of second weights, and using the Euclidean distances as the confidence degree information.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460563.9A CN113177466A (en) | 2021-04-27 | 2021-04-27 | Identity recognition method and device based on face image, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110460563.9A CN113177466A (en) | 2021-04-27 | 2021-04-27 | Identity recognition method and device based on face image, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113177466A true CN113177466A (en) | 2021-07-27 |
Family
ID=76926607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110460563.9A Pending CN113177466A (en) | 2021-04-27 | 2021-04-27 | Identity recognition method and device based on face image, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177466A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113553971A (en) * | 2021-07-29 | 2021-10-26 | 青岛以萨数据技术有限公司 | Method and device for extracting optimal frame of face sequence and storage medium |
| CN114863506A (en) * | 2022-03-18 | 2022-08-05 | 珠海优特电力科技股份有限公司 | Method, device and system for verifying access permission and identity authentication terminal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101266704A (en) * | 2008-04-24 | 2008-09-17 | 张宏志 | ATM secure authentication and pre-alarming method based on face recognition |
| CN101329724A (en) * | 2008-07-29 | 2008-12-24 | 上海天冠卫视技术研究所 | Optimized human face recognition method and apparatus |
| US20110135165A1 (en) * | 2009-06-02 | 2011-06-09 | Harry Wechsler | Robust Human Authentication Using Holistic Anthropometric and Appearance-Based Features and Boosting |
| CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
| CN104778462A (en) * | 2015-04-28 | 2015-07-15 | 哈尔滨理工大学 | Face recognition method and device |
| CN108189804A (en) * | 2017-12-29 | 2018-06-22 | 威马智慧出行科技（上海）有限公司 | A kind of face identification system and face identification method for vehicle |
| CN109377544A (en) * | 2018-11-30 | 2019-02-22 | 腾讯科技（深圳）有限公司 | A kind of face three-dimensional image generating method, device and readable medium |
| CN112614213A (en) * | 2020-12-14 | 2021-04-06 | 杭州网易云音乐科技有限公司 | Facial expression determination method, expression parameter determination model, medium and device |
-
2021
- 2021-04-27 CN CN202110460563.9A patent/CN113177466A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101266704A (en) * | 2008-04-24 | 2008-09-17 | 张宏志 | ATM secure authentication and pre-alarming method based on face recognition |
| CN101329724A (en) * | 2008-07-29 | 2008-12-24 | 上海天冠卫视技术研究所 | Optimized human face recognition method and apparatus |
| US20110135165A1 (en) * | 2009-06-02 | 2011-06-09 | Harry Wechsler | Robust Human Authentication Using Holistic Anthropometric and Appearance-Based Features and Boosting |
| CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
| CN104778462A (en) * | 2015-04-28 | 2015-07-15 | 哈尔滨理工大学 | Face recognition method and device |
| CN108189804A (en) * | 2017-12-29 | 2018-06-22 | 威马智慧出行科技（上海）有限公司 | A kind of face identification system and face identification method for vehicle |
| CN109377544A (en) * | 2018-11-30 | 2019-02-22 | 腾讯科技（深圳）有限公司 | A kind of face three-dimensional image generating method, device and readable medium |
| CN112614213A (en) * | 2020-12-14 | 2021-04-06 | 杭州网易云音乐科技有限公司 | Facial expression determination method, expression parameter determination model, medium and device |
Non-Patent Citations (3)
| Title |
|---|
| 党鑫鹏，刘文萍: "基于多级纹理频谱特征与 PCA 的人脸识别算法", 《计算机应用》 * |
| 孔祥玉: "《广义主成分分析算法及应用》", 31 July 2018, 国防工业出版社 * |
| 韩跃平: "《X射线视觉自动检测技术及应用》", 30 November 2012, 国防工业出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113553971A (en) * | 2021-07-29 | 2021-10-26 | 青岛以萨数据技术有限公司 | Method and device for extracting optimal frame of face sequence and storage medium |
| CN114863506A (en) * | 2022-03-18 | 2022-08-05 | 珠海优特电力科技股份有限公司 | Method, device and system for verifying access permission and identity authentication terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114187624B (en) | Image generation method, device, electronic equipment and storage medium | |
| CN113963110B (en) | Texture map generation method and device, electronic equipment and storage medium | |
| CN112818227B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN113177472A (en) | Dynamic gesture recognition method, device, equipment and storage medium | |
| CN112580666A (en) | Image feature extraction method, training method, device, electronic equipment and medium | |
| CN113591566A (en) | Training method and device of image recognition model, electronic equipment and storage medium | |
| CN113221771A (en) | Living body face recognition method, living body face recognition device, living body face recognition equipment, storage medium and program product | |
| CN112861885A (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN113177466A (en) | Identity recognition method and device based on face image, electronic equipment and medium | |
| CN113947188A (en) | Training method of target detection network and vehicle detection method | |
| CN114332977A (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN113177449A (en) | Face recognition method and device, computer equipment and storage medium | |
| CN114120454A (en) | Training method and device of living body detection model, electronic equipment and storage medium | |
| CN113947189A (en) | Training method and device for image generation model, electronic equipment and storage medium | |
| CN113379877A (en) | Face video generation method and device, electronic equipment and storage medium | |
| CN113052962A (en) | Model training method, information output method, device, equipment and storage medium | |
| CN115393488B (en) | Method and device for driving virtual character expression, electronic equipment and storage medium | |
| CN114267375B (en) | Phoneme detection method and device, training method and device, equipment and medium | |
| CN112560848B (en) | Training method and device for POI (Point of interest) pre-training model and electronic equipment | |
| CN115565186A (en) | Method and device for training character recognition model, electronic equipment and storage medium | |
| CN113361363B (en) | Training method, device, equipment and storage medium for face image recognition model | |
| CN113781653B (en) | Object model generation method and device, electronic equipment and storage medium | |
| CN113903071A (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN114093006A (en) | Training method, device and equipment of living human face detection model and storage medium | |
| CN114445668A (en) | Image recognition method and device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210727 |
|
| RJ01 | Rejection of invention patent application after publication |