CN114882569A - Voiceprint image combined face recognition method, device, equipment and storage medium - Google Patents
Voiceprint image combined face recognition method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114882569A CN114882569A CN202210604454.4A CN202210604454A CN114882569A CN 114882569 A CN114882569 A CN 114882569A CN 202210604454 A CN202210604454 A CN 202210604454A CN 114882569 A CN114882569 A CN 114882569A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- recognition
- face
- living body
- video
- 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
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 27
- 230000009471 action Effects 0.000 claims description 18
- 230000004913 activation Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 2
- 230000009977 dual effect Effects 0.000 claims 1
- 230000011218 segmentation Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000004397 blinking Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a biological recognition technology, and discloses a face recognition method combining voiceprint images, which comprises the following steps: acquiring a monitoring video, and performing face living body recognition on the monitoring video according to a preset face recognition method to obtain a face recognition result; when the face recognition result passes the authentication, acquiring audio information in the monitoring video, and performing voiceprint authentication on the audio information by using a pre-trained voiceprint recognition network to obtain a voiceprint recognition result; and when the voiceprint recognition result passes the authentication, screening people from a pre-constructed face database according to the face recognition result to obtain the identity information of the people in the monitoring video. The invention also provides a face recognition device, electronic equipment and storage medium combined with the voiceprint image. The invention can reduce the risk degree of the face recognition attacked by the network.
Description
Technical Field
The invention relates to the technical field of biological recognition, in particular to a voiceprint image combined face recognition method and device, electronic equipment and a computer readable storage medium.
Background
The application of face recognition in the field of artificial intelligence is more and more extensive, for example, payment authentication, login authentication and the like, however, with the development of internet technology, some network attack behaviors also appear in society to attack face recognition technology, such as people's photos and the like, so that face misjudgment is caused, and thus, infringement is caused to users. At present, in a network, living body detection technologies such as 3D environment recognition, ambient light recognition, specific behavior instruction recognition and the like exist to enhance the safety of face recognition, however, due to the development of 3D printing and real human mask technologies, a single image recognition gradually cannot recognize network attack behaviors which are advanced with time. Therefore, a more rigorous and accurate network attack recognition method is needed to reduce the risk of network attack on face recognition.
Disclosure of Invention
The invention provides a voiceprint image combined face recognition method and device and a computer readable storage medium, and mainly aims to reduce the risk degree of network attack on face recognition.
In order to achieve the above object, the present invention provides a face recognition method combining voiceprint images, comprising:
acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and performing face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
when the living body identification result passes the authentication, carrying out voiceprint identification on the audio information by using a voiceprint identification network in the image audio dual-channel face identification model to obtain a voiceprint identification result;
and when the voiceprint recognition result passes the authentication, screening people from a pre-constructed face database according to the face characteristic result to obtain the identity information of the people in the monitoring video.
Optionally, the voiceprint recognition is performed on the audio information by using a voiceprint recognition network in the image audio dual-channel face recognition model to obtain a voiceprint recognition result, including:
carrying out voiceprint feature identification on the audio information to obtain a voiceprint feature set;
identifying the voiceprint feature set by using a spliced audio identification activation function in the voiceprint identification network, and judging whether the audio information is spliced audio;
when the audio information is spliced audio, generating a spliced audio attack alarm;
when the audio information is not spliced audio, acquiring prestored voiceprint information corresponding to the face recognition result, and recognizing the similarity between the voiceprint feature set and the prestored voiceprint information;
and obtaining a voiceprint recognition result of the audio information according to the similarity and a preset credible threshold.
Optionally, the performing living body face identification on the video image information to obtain a living body identification result and a face feature result includes:
carrying out graying processing on the monitoring video to obtain a grayscale video;
intercepting a living body authentication video from the gray level video according to a preset random living body identification method;
performing action feature recognition on the living body authentication video by using a living body recognition network in the image audio dual-channel face recognition model to obtain an authentication action set;
when the authentication action set does not conform to the random living body identification method, judging that a living body attack phenomenon exists in the monitoring video, and sending out a preset living body attack alarm;
and when the authentication action set conforms to the random living body identification method, judging that the character in the monitoring video is a living body, and performing feature identification on the gray level video by using a face feature extraction network in the image audio dual-channel face identification model to obtain a face feature result.
Optionally, the intercepting a living body authentication video from the grayscale video according to a preset random living body identification method includes:
randomly extracting an identification method from a pre-constructed living body identification method set;
and generating a face capturing frame according to the identification method, and capturing the face video in the face capturing frame to obtain the living body authentication video.
Optionally, the performing, by using a living body recognition network in the image audio dual-channel face recognition model, motion feature recognition on the living body authentication video to obtain an authentication motion set, including:
performing feature extraction operation on the living body authentication video by using the living body identification network to obtain a feature sequence set;
performing feature identification operation on the feature sequence set to obtain a feature set;
and carrying out classification judgment on the feature set to obtain an authentication action set.
Optionally, before the introducing the surveillance video into a pre-trained image-audio dual-channel face recognition model for video data division, the method further includes:
acquiring a voiceprint recognition network comprising a voiceprint matching activation function and an audio splicing judgment activation function;
acquiring a pre-constructed training sample set, sequentially extracting a training sample from the training sample set, and introducing the training sample into the voiceprint recognition network to obtain a recognition result;
calculating a loss value between the recognition result and a real result corresponding to the training sample according to a cross entropy algorithm;
minimizing the loss value to obtain a function parameter when the loss value is minimum, and reversely updating the voiceprint recognition network by using the function parameter to obtain an updated voiceprint recognition network;
judging the convergence of the loss value;
when the loss value is not converged, returning to the step of sequentially extracting a training sample from the training sample set and introducing the training sample into the voiceprint recognition network to obtain a recognition result, and performing iterative update on the updated voiceprint recognition network;
and when the loss value is converged, outputting the finally updated voiceprint recognition network to obtain the trained voiceprint recognition network.
Optionally, before performing living body face recognition on the video image information to obtain a living body recognition result and a face feature result, the method further includes:
carrying out mouth shape recognition on the monitoring video to obtain a mouth characteristic sequence;
performing sound lip matching by using the mouth feature sequence and the audio information;
when the voice and the lips are matched, performing voiceprint authentication on the audio information by using the pre-trained voiceprint recognition network to obtain a voiceprint recognition result;
and when the sound lip is not matched, giving out a preset sound lip mismatch alarm.
In order to solve the above problem, the present invention further provides a face recognition device combining voiceprint images, the face recognition device comprising:
the face authentication module is used for acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and carrying out face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
the voiceprint recognition module is used for carrying out voiceprint recognition on the audio information by using a voiceprint recognition network in the image audio dual-channel face recognition model when the living body recognition result passes the authentication so as to obtain a voiceprint recognition result;
and the identity information acquisition module is used for screening people from a pre-constructed face database according to the face characteristic result when the voiceprint recognition result passes the authentication so as to obtain the identity information of the people in the monitoring video.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the voiceprint image combined face recognition method described above.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the voiceprint image combined face recognition method described above.
According to the method and the device, whether a person in a monitored video is a living body or not is checked by using a face recognition method to obtain a face recognition result, and then whether audio information is an audio formed by intercepting and splicing or not is judged through a voiceprint recognition network and whether the audio information accords with a voiceprint corresponding to the face recognition result or not to obtain a final face recognition result. Therefore, the voiceprint image combined face recognition method, device, equipment and storage medium provided by the embodiment of the invention can reduce the risk degree of the face recognition attacked by the network.
Drawings
Fig. 1 is a schematic flow chart of a face recognition method by combining voiceprint images according to an embodiment of the present invention;
fig. 2 is a detailed flowchart illustrating a step in a voiceprint image combined face recognition method according to an embodiment of the present invention;
fig. 3 is a detailed flowchart illustrating a step in a voiceprint image combined face recognition method according to an embodiment of the present invention;
fig. 4 is a detailed flowchart illustrating a step in a voiceprint image combined face recognition method according to an embodiment of the present invention;
fig. 5 is a detailed flowchart illustrating a step in a voiceprint image combined face recognition method according to an embodiment of the present invention;
fig. 6 is a detailed flowchart illustrating a step in a voiceprint image combined face recognition method according to an embodiment of the present invention;
FIG. 7 is a functional block diagram of a face recognition apparatus incorporating a voiceprint image according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device for implementing the face recognition method based on voiceprint image combination according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a face recognition method combining voiceprint images. In this embodiment of the present application, an execution subject of the voiceprint image combined face recognition method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided in this embodiment of the present application. In other words, the voiceprint image combined face recognition method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Fig. 1 is a schematic flow chart of a face recognition method by combining voiceprint images according to an embodiment of the present invention. In this embodiment, the method for face recognition by combining voiceprint images includes steps S1 to S7:
s1, acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and performing face living body recognition on the video image information to obtain a living body recognition result and a face feature result.
In the embodiment of the invention, the monitoring video can be acquired by unlocking a device or a monitoring device of other equipment. Such as cell phone cameras, gate monitoring equipment, etc.
Further, in the embodiment of the present invention, the image-audio dual-channel face recognition model is a logistic regression classification cluster neural network controllable by a circuit channel, and is used for sequentially recognizing video image information and audio information.
The embodiment of the invention introduces the monitoring video into a pre-trained image audio dual-channel face recognition model, and performs data division on the monitoring video to obtain audio information and video image information, wherein the audio data and the video image data can be marked with a special label, such as '0' and '1'. The image audio dual-channel face recognition model calls different neural networks to perform parallel analysis according to the label of the imported data, and the data processing efficiency is improved. The embodiment of the invention performs the video data division operation according to the same time speed.
Further, referring to fig. 2, in the embodiment of the present invention, the performing living body face recognition on the video image information to obtain a living body recognition result and a face feature result includes steps S11 to S16:
s11, carrying out graying processing on the monitoring video to obtain a grayscale video;
s12, intercepting a living body authentication video from the gray level video according to a preset random living body identification method;
s13, performing action feature recognition on the living body authentication video by using a living body recognition network in the image audio dual-channel face recognition model to obtain an authentication action set;
s14, judging whether the authentication action set conforms to the random living body identification method;
when the authentication action set does not conform to the random living body identification method, S15, judging that a living body attack phenomenon exists in the monitoring video, and sending out a preset living body attack alarm;
and when the authentication action set conforms to the random living body identification method, S16, judging that the character in the monitoring video is a living body, and performing feature identification on the gray-scale video by using a face feature extraction network in the image audio dual-channel face identification model to obtain a face feature result.
Specifically, the embodiment of the invention performs gray calculation on the channel values of the three primary colors of red, green and blue through a gray algorithm to obtain the gray video, so that the data volume can be effectively reduced, and the video processing efficiency can be increased.
Further, referring to fig. 3, in the embodiment of the present invention, the step of step S12 includes steps S121-S122:
s121, randomly extracting an identification method from a pre-constructed living body identification method set;
and S122, generating a face capturing frame according to the identification method, and capturing the face video in the face capturing frame to obtain a living body authentication video.
In the embodiment of the invention, the living body identification method set comprises a plurality of living body detection instructions, such as detection instructions of blinking, turning left and right, opening mouth, and the like. Each living body identification method is randomly selected, and the living body identification safety is improved.
For example, when an identification method of random extraction is blink detection, a face contour is generated, a user places a face image in the face contour, and then the living body authentication video can be obtained by intercepting a video of an eye position in the face contour according to the blink detection method. Similarly, if the mouth opening test is selected, the video of the mouth position is intercepted.
Further, referring to fig. 4, in the embodiment of the present invention, the step S13 includes steps S131 to S133:
s131, performing feature extraction operation on the living body authentication video by using the living body identification network to obtain a feature sequence set;
s132, performing feature identification operation on the feature sequence set to obtain a feature set;
and S133, classifying and judging the feature set to obtain an authentication action set.
Specifically, in the embodiment of the present invention, a convolution pooling operation is performed on the living body authentication video through the feature extraction network to obtain a feature sequence set, a full connection operation is performed on the feature sequence set, each feature sequence in the feature sequence set is arranged and combined to obtain a feature set, and finally, the feature set is classified and judged, and features with scores greater than a qualified score, for example, 70% in the feature set are extracted to obtain an authentication action set, such as blinking, mouth opening, left-right head swinging, and other actions.
According to the recognition of the above steps S11-S16, whether the person in the monitored video is a living body or not and whether the person is a person pre-stored in the database or not can be analyzed and obtained.
S2, judging whether the face recognition result passes authentication;
when the face recognition result fails to pass the authentication, S3, generating an unsuccessful recognition prompt;
and when the face recognition result passes the authentication, S4, performing voiceprint recognition on the audio information by using a voiceprint recognition network in the image audio dual-channel face recognition model to obtain a voiceprint recognition result.
Specifically, in the embodiment of the present invention, the voiceprint recognition network is a decision tree forest network, and includes a voiceprint matching activation function and an audio splicing judgment activation function.
In detail, referring to fig. 5, in the embodiment of the present invention, the performing voiceprint recognition on the audio information by using the voiceprint recognition network in the image-audio dual-channel face recognition model to obtain a voiceprint recognition result includes steps S21 to S25:
s21, carrying out voiceprint feature recognition on the audio information to obtain a voiceprint feature set;
s22, identifying the voiceprint feature set by using a spliced audio identification activation function in the voiceprint identification network, and judging whether the audio information is spliced audio;
when the audio information is spliced audio, S23, generating a spliced audio attack alarm;
when the audio information is not the spliced audio, S24, obtaining pre-stored voiceprint information corresponding to the face recognition result, and recognizing the similarity between the voiceprint feature set and the pre-stored voiceprint information;
and S25, obtaining a voiceprint recognition result of the audio information according to the similarity and a preset credible threshold.
The embodiment of the invention utilizes the voiceprint recognition network to recognize whether the audio information is manually intercepted and spliced or not on the one hand, and to recognize whether the audio information corresponds to the prestored voiceprint information corresponding to the face recognition result or not on the other hand, so that whether the figure in the video is the real person or not and the voice of the person can be known.
Further, referring to fig. 6, in the embodiment of the present invention, before the introducing the surveillance video into the pre-trained image-audio dual-channel face recognition model for video data division, the method further includes steps S201 to S206:
s201, acquiring a voiceprint recognition network comprising a voiceprint matching activation function and an audio splicing judgment activation function;
s202, acquiring a pre-constructed training sample set, sequentially extracting a training sample from the training sample set, and introducing the training sample into the voiceprint recognition network to obtain a recognition result;
s203, calculating a loss value between the recognition result and a real result corresponding to the training sample according to a cross entropy algorithm;
s204, minimizing the loss value to obtain a function parameter when the loss value is minimum, and reversely updating the voiceprint recognition network by using the function parameter to obtain an updated voiceprint recognition network;
s205, judging the convergence of the loss value;
when the loss value is not converged, returning to the step of sequentially extracting a training sample from the training sample set and introducing the training sample into the voiceprint recognition network to obtain a recognition result, and performing iterative update on the updated voiceprint recognition network;
and S206, outputting the finally updated voiceprint recognition network when the loss value is converged to obtain the trained voiceprint recognition network.
In the embodiment of the invention, a training sample set is used for carrying out forward propagation calculation in the voiceprint recognition network to obtain a recognition matching score and a splicing judgment score, then the recognition matching score and the splicing judgment score are compared with the real result of the training sample to calculate the loss value of the training sample, the loss value is minimized by a gradient descent method to obtain a function parameter with the minimum loss value, the function parameter is subjected to network reverse transmission to update the voiceprint recognition network, so that a training process is completed, and a new training sample is extracted from the training sample set for training.
The loss value is the difference between the measured predicted value and the true value and is expressed by a variance value, so that when the loss value is converged, the difference between the predicted result and the true result of the voiceprint recognition network is small and relatively stable, and the voiceprint recognition network is trained. In the embodiment of the present invention, the variation range of the variation curve of the loss value in a preset time period may be calculated, and the convergence may be determined.
The embodiment of the invention leads the audio information into the trained voiceprint recognition network, thereby obtaining the voiceprint recognition result.
Further, in another embodiment of the present invention, before performing living body face recognition on the video image information to obtain a living body recognition result and a face feature result, the method further includes: carrying out mouth shape recognition on the monitoring video to obtain a mouth characteristic sequence; performing sound lip matching by using the mouth feature sequence and the audio information; when the voice and the lips are matched, performing voiceprint authentication on the audio information by using the pre-trained voiceprint recognition network to obtain a voiceprint recognition result; and when the sound lip is not matched, giving out a preset sound lip mismatch alarm.
In another embodiment of the invention, whether the images and the sounds in the monitoring video are matched can be judged in advance through sound lip matching, so that whether the network identification attack is detected in advance.
S5, judging whether the voiceprint recognition result passes authentication;
when the voiceprint recognition result is not authenticated, S6, generating a preset alarm;
and when the voiceprint recognition result passes the authentication, S7, screening people from a pre-constructed human face database according to the human face feature result, and obtaining the identity information of the people in the monitoring video.
Specifically, when the voiceprint recognition result passes the authentication, it is indicated that the person in the monitored image is the person himself, and then the person is on site, so that the characteristics in the face characteristic result are inquired from a pre-constructed face database, and further the identity information of the person in the monitored video is obtained.
According to the embodiment of the application, a face recognition method is firstly utilized to check whether a person in a monitored video is a living body or not to obtain a face recognition result, then whether audio information is audio formed by intercepting and splicing or not is judged through a voiceprint recognition network, whether the audio information accords with the face recognition result or not, and finally the face recognition result is obtained. Therefore, the voiceprint image combined face recognition method provided by the embodiment of the invention can reduce the risk degree of the face recognition attacked by the network.
Fig. 7 is a functional block diagram of a face recognition apparatus combined with a voiceprint image according to an embodiment of the present invention.
The face recognition apparatus 100 combined with the voiceprint image according to the present invention can be installed in an electronic device. According to the implemented functions, the face recognition apparatus 100 combining the voiceprint images may include a face authentication module 101, a voiceprint recognition module 102, and an identity information acquisition module 103. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the face authentication module 101 is configured to acquire a surveillance video, import the surveillance video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and perform face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
the voiceprint recognition module 102 is configured to perform voiceprint recognition on the audio information by using a voiceprint recognition network in the image audio dual-channel face recognition model when the living body recognition result passes the authentication, so as to obtain a voiceprint recognition result;
the identity information obtaining module 103 is configured to, when the voiceprint recognition result passes the authentication, screen a person from a pre-constructed face database according to the face feature result, and obtain identity information of the person in the monitoring video.
In detail, when the modules in the face recognition apparatus 100 combined with a voiceprint image in the embodiment of the present application are used, the same technical means as the above-mentioned face recognition method combined with a voiceprint image in fig. 1 to 3 is adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 8 is a schematic structural diagram of an electronic device implementing a face recognition method by combining voiceprint images according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a voiceprint image combined face recognition program, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., a face recognition program for performing voiceprint image combination, etc.) stored in the memory 11 and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of a voiceprint image combined face recognition program, etc., but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 8 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 8 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The voiceprint image combined face recognition program stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, which when executed in the processor 10, can implement:
acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and performing face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
when the living body identification result passes the authentication, carrying out voiceprint identification on the audio information by using a voiceprint identification network in the image audio dual-channel face identification model to obtain a voiceprint identification result;
and when the voiceprint recognition result passes the authentication, screening people from a pre-constructed face database according to the face characteristic result to obtain the identity information of the people in the monitoring video.
Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and performing face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
when the living body identification result passes the authentication, carrying out voiceprint identification on the audio information by using a voiceprint identification network in the image audio dual-channel face identification model to obtain a voiceprint identification result;
and when the voiceprint recognition result passes the authentication, screening people from a pre-constructed face database according to the face characteristic result to obtain the identity information of the people in the monitoring video.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A face recognition method combining voiceprint images is characterized by comprising the following steps:
acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and performing face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
when the living body identification result passes the authentication, carrying out voiceprint identification on the audio information by using a voiceprint identification network in the image audio dual-channel face identification model to obtain a voiceprint identification result;
and when the voiceprint recognition result passes the authentication, screening people from a pre-constructed face database according to the face characteristic result to obtain the identity information of the people in the monitoring video.
2. The method for recognizing a face by combining the voiceprint images according to claim 1, wherein the voiceprint recognition network in the image audio dual-channel face recognition model is used for carrying out voiceprint recognition on the audio information to obtain a voiceprint recognition result, and the method comprises the following steps:
carrying out voiceprint feature identification on the audio information to obtain a voiceprint feature set;
identifying the voiceprint feature set by using a spliced audio identification activation function in the voiceprint identification network, and judging whether the audio information is spliced audio;
when the audio information is spliced audio, generating a spliced audio attack alarm;
when the audio information is not spliced audio, acquiring prestored voiceprint information corresponding to the face recognition result, and recognizing the similarity between the voiceprint feature set and the prestored voiceprint information;
and obtaining a voiceprint recognition result of the audio information according to the similarity and a preset credible threshold.
3. The method for recognizing a face by combining voiceprint images according to claim 1, wherein the performing living body recognition on the face of the video image information to obtain a living body recognition result and a face feature result comprises:
carrying out graying processing on the monitoring video to obtain a grayscale video;
intercepting a living body authentication video from the gray level video according to a preset random living body identification method;
performing action feature recognition on the living body authentication video by using a living body recognition network in the image audio dual-channel face recognition model to obtain an authentication action set;
when the authentication action set does not accord with the random living body identification method, judging that a living body attack phenomenon exists in the monitoring video, and sending out a preset living body attack alarm;
and when the authentication action set conforms to the random living body identification method, judging that the character in the monitoring video is a living body, and performing feature identification on the gray level video by using a face feature extraction network in the image audio dual-channel face identification model to obtain a face feature result.
4. The voiceprint image combined face recognition method according to claim 3, wherein the capturing the living body authentication video from the gray level video according to a preset random living body recognition method comprises:
randomly extracting an identification method from a pre-constructed living body identification method set;
and generating a face capturing frame according to the identification method, and capturing the face video in the face capturing frame to obtain the living body authentication video.
5. The method for recognizing a face by combining voiceprint images according to claim 3, wherein the performing motion feature recognition on the living body authentication video by using a living body recognition network in the image audio dual-channel face recognition model to obtain an authentication motion set comprises:
performing feature extraction operation on the living body authentication video by using the living body identification network to obtain a feature sequence set;
performing feature identification operation on the feature sequence set to obtain a feature set;
and carrying out classification judgment on the feature set to obtain an authentication action set.
6. The method of voiceprint image combined face recognition according to claim 1, wherein before the introducing the surveillance video into a pre-trained image audio dual channel face recognition model for video data segmentation, the method further comprises:
acquiring a voiceprint recognition network comprising a voiceprint matching activation function and an audio splicing judgment activation function;
acquiring a pre-constructed training sample set, sequentially extracting a training sample from the training sample set, and introducing the training sample into the voiceprint recognition network to obtain a recognition result;
calculating a loss value between the recognition result and a real result corresponding to the training sample according to a cross entropy algorithm;
minimizing the loss value to obtain a function parameter when the loss value is minimum, and reversely updating the voiceprint recognition network by using the function parameter to obtain an updated voiceprint recognition network;
judging the convergence of the loss value;
when the loss value is not converged, returning to the step of sequentially extracting a training sample from the training sample set and introducing the training sample into the voiceprint recognition network to obtain a recognition result, and performing iterative update on the updated voiceprint recognition network;
and when the loss value is converged, outputting the finally updated voiceprint recognition network to obtain the trained voiceprint recognition network.
7. The method for face recognition by combining voiceprint images according to claim 1, wherein before the face living body recognition is performed on the video image information to obtain a living body recognition result and a face feature result, the method further comprises:
carrying out mouth shape recognition on the monitoring video to obtain a mouth characteristic sequence;
performing sound lip matching by using the mouth feature sequence and the audio information;
when the voice and the lips are matched, performing voiceprint authentication on the audio information by using the pre-trained voiceprint recognition network to obtain a voiceprint recognition result;
and when the sound lip is not matched, giving out a preset sound lip mismatch alarm.
8. A voiceprint image integrated face recognition apparatus, the apparatus comprising:
the face authentication module is used for acquiring a monitoring video, importing the monitoring video into a pre-trained image audio dual-channel face recognition model for video data division to obtain audio information and video image information, and carrying out face living body recognition on the video image information to obtain a living body recognition result and a face feature result;
the voiceprint recognition module is used for carrying out voiceprint recognition on the audio information by using a voiceprint recognition network in the image audio dual-channel face recognition model when the living body recognition result passes the authentication so as to obtain a voiceprint recognition result;
and the identity information acquisition module is used for screening people from a pre-constructed face database according to the face characteristic result when the voiceprint recognition result passes the authentication so as to obtain the identity information of the people in the monitoring video.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a method of voiceprint image combined face recognition as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method for voiceprint image combined face recognition according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210604454.4A CN114882569A (en) | 2022-05-30 | 2022-05-30 | Voiceprint image combined face recognition method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210604454.4A CN114882569A (en) | 2022-05-30 | 2022-05-30 | Voiceprint image combined face recognition method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114882569A true CN114882569A (en) | 2022-08-09 |
Family
ID=82678993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210604454.4A Pending CN114882569A (en) | 2022-05-30 | 2022-05-30 | Voiceprint image combined face recognition method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114882569A (en) |
-
2022
- 2022-05-30 CN CN202210604454.4A patent/CN114882569A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112395978B (en) | Behavior detection method, behavior detection device and computer readable storage medium | |
| CN112507936B (en) | Image information auditing method and device, electronic equipment and readable storage medium | |
| CN111681681A (en) | Voice emotion recognition method and device, electronic equipment and storage medium | |
| CN111898538B (en) | Certificate authentication method and device, electronic equipment and storage medium | |
| CN112651342B (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN112396005A (en) | Biological characteristic image recognition method and device, electronic equipment and readable storage medium | |
| CN112581227A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN112989334A (en) | Data detection method for machine learning and related equipment | |
| CN113869219A (en) | Face living body detection method, device, equipment and storage medium | |
| CN115471775A (en) | Information verification method, device and equipment based on screen recording video and storage medium | |
| CN115661531A (en) | Image-text-based early oral cancer identification method, device, equipment and storage medium | |
| CN114677650A (en) | Intelligent analysis method and device for pedestrian illegal behaviors of subway passengers | |
| CN114639152A (en) | Multi-modal voice interaction method, device, equipment and medium based on face recognition | |
| CN112686232B (en) | Teaching evaluation method and device based on micro expression recognition, electronic equipment and medium | |
| CN113486316A (en) | User identity authentication method and device, electronic equipment and readable storage medium | |
| CN113792801B (en) | Method, device, equipment and storage medium for detecting face dazzling degree | |
| CN113887408B (en) | Method, device, equipment and storage medium for detecting activated face video | |
| CN112101192B (en) | Artificial intelligence-based camouflage detection method, device, equipment and medium | |
| CN114882569A (en) | Voiceprint image combined face recognition method, device, equipment and storage medium | |
| CN113920590A (en) | Living body detection method, living body detection device, living body detection equipment and readable storage medium | |
| CN115099339A (en) | Fraud behavior identification method and device, electronic equipment and storage medium | |
| CN115037790A (en) | Abnormal registration identification method, device, equipment and storage medium | |
| CN114049676A (en) | Fatigue state detection method, device, equipment and storage medium | |
| CN113505698A (en) | Face recognition method, device, equipment and medium based on counterstudy |
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 |