CN111767840A - Method, apparatus, electronic device and computer-readable storage medium for verifying image - Google Patents
Method, apparatus, electronic device and computer-readable storage medium for verifying image Download PDFInfo
- Publication number
- CN111767840A CN111767840A CN202010603371.4A CN202010603371A CN111767840A CN 111767840 A CN111767840 A CN 111767840A CN 202010603371 A CN202010603371 A CN 202010603371A CN 111767840 A CN111767840 A CN 111767840A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- user
- face image
- feature information
- 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 55
- 238000012216 screening Methods 0.000 claims abstract description 55
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000004044 response Effects 0.000 claims description 28
- 230000015654 memory Effects 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 210000003128 head Anatomy 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- 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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for verifying an image, electronic equipment and a computer-readable storage medium, and relates to the technical field of computers, the technical field of image processing, the technical field of artificial intelligence, the technical field of face recognition, the technical field of image auditing, the technical field of neural networks and the technical field of deep learning. The specific implementation scheme is as follows: analyzing whether a face image area meeting a predetermined condition is contained in an image uploaded by a user; if the face image area contains at least one face image area, detecting whether face characteristic information contained in the face image area meets the preset screening requirement or not; if yes, obtaining an authenticated face image of the user, and calculating the similarity between the authenticated face image and face feature information contained in the face image; and when the similarity meets a preset threshold condition, verifying that the image uploaded by the user is a qualified image. The scheme provides a method for verifying the image, the user is refused to upload and use the image with infringement risk, and the auditing is efficiently completed.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to the technical field of image processing, the technical field of artificial intelligence, the technical field of face recognition, the technical field of image auditing, the technical field of neural networks and the technical field of deep learning.
Background
Currently, a social networking platform allows a user to set account images (such as head portraits and signatures) that the user likes according to the needs of the user, so as to achieve the purpose of authenticating and distinguishing the user according to the account images.
In the process of uploading images by users, some users upload photos of others as their own images, which not only infringes the portraits of others, but also may cause other users to misunderstand users of account numbers in some social networking platforms with high requirements on real-name information, thereby bringing unnecessary risks to the platforms and other users.
Therefore, the social platform often needs to perform identity verification on images containing real faces uploaded by users.
Disclosure of Invention
The application provides a method, a device, an electronic device and a storage medium for verifying an image.
In a first aspect, an embodiment of the present application provides a method for verifying an image, including: acquiring a user uploaded image, and analyzing whether the user uploaded image contains a face image area meeting a predetermined condition; in response to the fact that the user uploaded image contains at least one face image area, detecting whether face feature information contained in the face image area meets preset screening requirements or not; in response to the fact that the face feature information meets the preset screening requirement, an authenticated face image of the user is obtained, and the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image is calculated; and in response to determining that the similarity meets a preset threshold condition, determining that the image uploaded by the user is a qualified image.
In a second aspect, an embodiment of the present application provides an apparatus for authenticating an image, including: the image acquisition unit is configured to acquire a user uploading image and analyze whether the user uploading image contains a face image area meeting a predetermined condition; the image screening unit is configured to respond to the fact that at least one face image area is contained in the uploaded image of the user, and detect whether face feature information contained in the face image area meets the preset screening requirement or not; the image comparison unit is configured to respond to the fact that the face feature information meets the preset screening requirement, obtain an authenticated face image of the user, and calculate the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image; and the first image verification unit is configured to respond to the fact that the similarity meets the preset threshold condition, and determine that the image uploaded by the user is a qualified image.
In a third aspect, an embodiment of the present application provides an electronic device, including: 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 a method for authenticating an image as described in any implementation of the first aspect.
In a fourth aspect, embodiments of the present application provide a non-transitory computer readable storage medium having computer instructions stored thereon, comprising: the computer instructions are for causing the computer to perform a method for authenticating an image as described in any implementation form of the first aspect.
The method for verifying the image in the embodiment of the application acquires the image uploaded by the user, and analyzes whether the image uploaded by the user contains a face image area meeting a predetermined condition; after determining that the image uploaded by the user comprises at least one face image area, detecting whether face feature information contained in the face image area meets preset screening requirements or not; after the face feature information is determined to meet the preset screening requirement, an authenticated face image of the user is obtained, and the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image is calculated; and determining that the similarity meets a preset threshold condition, determining that the image uploaded by the user is a qualified image so as to achieve the purpose of judging whether infringement content exists in the image uploaded by the user, and determining a corresponding auditing strategy (for example, the image verified to be qualified is not audited any more, only the unqualified image is audited) according to different results of image verification in the subsequent auditing process, so that the auditing efficiency can be improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is an exemplary system architecture to which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for authenticating an image according to the present application;
FIG. 3 is a schematic diagram of a predetermined conditional analysis flow of one embodiment of a method for authenticating an image according to the present application;
FIG. 4 is a schematic diagram of a preset screening condition detection flow of an embodiment of the method for verifying an image of the present application;
FIG. 5 is a schematic block diagram of one embodiment of an apparatus for authenticating an image according to the present application;
FIG. 6 is a block diagram of an electronic device suitable for use in implementing the method for authenticating an image of an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. 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 application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the method, apparatus, electronic device, and computer-readable storage medium for authenticating images of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send pictures or the like. Various social client applications, such as forum-like applications, friend-making-like applications, search-like applications, etc., may be installed on the terminal devices 101, 102, 103.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as a plurality of software or software modules (for example to implement a service for verifying images) or as a single software or software module. And is not particularly limited herein.
The server 105 may be a server providing various services, for example, an image uploaded by the terminal devices 101, 102, and 103 used by the user is displayed and received in the present application through the network 104, whether a face image region meeting a predetermined condition is included in the image is analyzed, whether face feature information in the face image region meets a preset screening requirement is determined when the face feature information included in the face image region meets the preset screening requirement is determined, if the face feature information meets the preset screening requirement, an authenticated face image of the user is obtained for comparison, and when a similarity of a comparison result meets a preset threshold condition, the image is used for verification as a qualified image, and the user is allowed to use the image.
It should be noted that the method for authenticating an image provided in the following embodiments of the present application is generally performed by the server 105, and accordingly, the apparatus for authenticating an image is generally disposed in the server 105.
It should be noted that both the image uploaded by the user and the authenticated face image of the user may be stored locally in the server 105, or the data may be dispersedly stored in the terminal devices 101, 102, and 103 according to all possible storage special requirements in an actual application scenario, where the storage terminal devices 101, 102, and 103 may be original documents or backup documents, and this is not limited specifically here. The exemplary system architecture 100 may also not include the terminal devices 101, 102, 103 and the network 104 when the terminal devices 101, 102, 103 are virtual machines running on the server 105.
It should be further noted that the terminal devices 101, 102, and 103 may also be installed with an application for verifying an image, and the terminal devices 101, 102, and 103 may also complete acquiring an image uploaded by a user, analyze whether the image includes a face image region that meets a predetermined condition, determine whether face feature information in the face image region meets a preset screening requirement when the image includes the face image region, if so, acquire an authenticated face image of the user for comparison, and when a similarity of a comparison result meets a preset threshold condition, determine that the image is a qualified image, and allow the user to use the image. At this time, the method for authenticating the image may also be executed by the terminal apparatuses 101, 102, 103, and accordingly, the means for authenticating the image may also be provided in the terminal apparatuses 101, 102, 103. At this point, the exemplary system architecture 100 may also not include the server 105 and the network 104.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (for example, for providing a push information service), or may be implemented as a single software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for authenticating an image according to the present application is shown. The method for verifying an image comprises the following steps:
In this embodiment, an execution subject (for example, the server 105 or the terminal devices 101, 102, 103 shown in fig. 1) for verifying an image may acquire a user upload image from a local or non-local human-computer interaction device (for example, the terminal devices 101, 102, 103 shown in fig. 1).
Specifically, the image uploaded by the user refers to an image which is uploaded by the user according to the preference of the user, the user can input the image into the execution main body for image verification (equivalent to a process of pre-reviewing the image) when uploading the image, and the execution main body can actively acquire and verify the image which is determined and uploaded by the user after the user determines and finishes uploading the image, so that the image is checked and self-checked in real time.
After the execution main body acquires the user uploaded image, pixels suspected to be a face in the image can be acquired, the image is detected by detecting the content of the pixels, whether the user uploaded image contains a face image area meeting a predetermined condition or not is analyzed, and whether the image contains a real face image or not is judged.
The predetermined condition may be determined according to experience of a person skilled in the art or a requirement of an actual application scenario, and is not limited in this application. For example, the predetermined condition may correspond to the above-mentioned manner of detecting the content in the image, so as to analyze that the face image in the face image region in the image that includes the face image region satisfying the predetermined condition corresponds to a real face.
In some optional implementations of the embodiment, the predetermined condition includes at least one of: the face confidence, the non-cartoon confidence, the race confidence, the maximum width and height of the face and the maximum width and height of the face image pixel in the face image region meet the threshold condition.
Specifically, the predetermined condition includes at least one of: the face confidence, the non-cartoon confidence, the race confidence, the face maximum width and height value and the face image pixel maximum width and height ratio of the face image region meet respective corresponding threshold conditions, the uploaded images of the user are analyzed, the predetermined conditions can be met simultaneously according to different predetermined conditions, or one or more conditions can be selected to analyze the uploaded images of the user to determine that the uploaded images of the user comprise at least one face image region, the images in the face image region are real face images, the uploaded images of the user are analyzed by using the predetermined conditions, so that the uploaded images of the user are screened, images of landscape and cartoon characters, for example, are removed, and the checking workload is reduced.
As shown in fig. 3 for example, to improve the accuracy of the determination, predetermined conditions are set to that a face image region in an acquired image needs to satisfy a face confidence degree greater than or equal to 0.9, a non-cartoon confidence degree greater than 0.7, a race confidence degree greater than 0.7, pixel values of a maximum width and a high value of a face in the image are greater than 50 pixels respectively, and pixel values of the maximum width and the high value of the face are greater than 10% of a picture width and a high total pixel value respectively, and when the predetermined conditions are satisfied, it is determined that a real face image exists in an image uploaded by the user.
In this embodiment, after the image uploaded by the user is analyzed in step 201, it is determined that the image includes at least one face image region (i.e., a region where a real face image exists) meeting a predetermined condition, the content in the region is detected according to a preset screening requirement, and it is determined whether the face feature information included in the face image in the region can support face image comparison.
The preset screening requirement may generally consider factors such as the degree of sharpness and the shielding ratio of the face in the image, for example, when comparing the face in the face image region with the face in the authenticated face image using the eye feature similarity, it is necessary to set that both eyes of the face in the face image region are open, or when comparing the face feature similarity, the preset screening condition is that the face shielding ratio cannot exceed the confidence threshold.
In some optional implementations of this embodiment, the preset screening requirement includes at least one of: the shielding ratio of the image of the face in the face image area is less than 0.5, the fuzzy ratio is less than 0.5, the three-dimensional rotation angle is less than 20 degrees up and down, the three-dimensional rotation angle is less than 30 degrees left and right, the sunglasses confidence coefficient is less than 0.9, and both eyes are in a non-closed state.
Specifically, the preset screening requirement may be a shielding ratio, a fuzzy ratio, a three-dimensional rotation angle up-down angle, a three-dimensional rotation angle left-right angle, a sunglasses confidence satisfying respective corresponding threshold conditions, and both eyes being in a non-closed state, so as to screen the user uploaded image, and if the face image area included in the user uploaded image fails to satisfy the preset screening requirement, it indicates that the face image area included in the user uploaded image cannot be subsequently used to compare with an authenticated face image of the user, or the comparison result has a large error, so that the part of the user uploaded images are removed, so as to improve the process efficiency and the verification accuracy.
As shown in fig. 4, for high-quality image screening, the preset screening conditions are set as: meanwhile, the shielding ratio is less than 0.5, the fuzzy ratio is less than 0.5, the three-dimensional rotation is not more than 20 degrees and 30 degrees respectively up and down and left and right, the confidence coefficient of the sunglasses is less than 0.9, and both eyes are not closed. Therefore, high-quality image screening is realized, and the face characteristic information contained in the obtained face region meets the requirement of comparing the subsequent face characteristic information with the authenticated face image.
In this embodiment, after the steps 201 and 202 are performed, a real and accurate real face image that is included in the uploaded image of the user and can be used for comparing with the authenticated face image of the user can be obtained, the real face image is compared with the authenticated face image of the user, and the similarity of the face feature information included in the two images is calculated.
The authenticated image refers to an image which is authenticated by the user through real-name authentication or legal authentication and can prove the identity information of the user, and the authenticated image of the user can be uploaded by the user or acquired from a local or other storage device through the execution.
It should be understood that, if there are a plurality of face image regions that satisfy a predetermined condition (for example, images uploaded by a user are a group), it is determined whether each face image region satisfies a preset screening requirement, and the similarity is calculated for the face image regions that satisfy the preset screening requirement one by one, and a plurality of similarity calculation results are output.
And step 204, in response to the fact that the similarity meets a preset threshold condition, determining that the image uploaded by the user is a qualified image.
In this embodiment, according to the similarity of the face feature information calculated in step 203, when the similarity satisfies a preset threshold condition, it is determined that the face image included in the uploaded image of the user is the same person as the face image included in the authenticated face image of the user, that is, the face included in the uploaded image of the user is of the user himself, the uploaded image of the user is a qualified image, and the user is allowed to use the qualified image.
It should be understood that when a plurality of similarity calculation results exist, as long as one of the similarity calculation results meets a preset threshold condition (that is, a face included in the user uploaded image is of the user), the user uploaded image can be verified to be a qualified image.
The method for verifying the image, provided by the embodiment of the application, comprises the steps of acquiring an image uploaded by a user, and analyzing whether the image uploaded by the user contains a face image area meeting a predetermined condition; in response to the fact that the user uploaded image contains at least one face image area, detecting whether face feature information contained in the face image area meets preset screening requirements or not; in response to the fact that the face feature information meets the preset screening requirement, an authenticated face image of the user is obtained, and the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image is calculated; and responding to the fact that the similarity meets the preset threshold value condition, and enabling the image uploaded by the user to be a qualified image. By the method for verifying the image, the image which is uploaded by the user and contains the real face can be efficiently screened and verified, so that the image verification efficiency is improved.
In some optional implementations of this embodiment, the step of acquiring the authenticated face image of the user in step 203 includes: acquiring an identity card image of the user, and extracting face feature information contained in the identity card image of the user by adopting a pre-trained extraction neural network; and in response to the fact that the extracted face feature information meets the requirement of a predetermined credibility threshold, taking a face image contained in the identity card image as an authenticated face image of the user.
Specifically, an identity card image of a user can be used as an original image to obtain an authenticated image of the user, and a pre-trained extraction neural network is used for extracting features of a portrait image in the identity card image to obtain face feature information contained in the identity card image of the user; when the face feature information contained in the identity card image of the user meets the requirement of a predetermined credibility threshold, the face image contained in the identity card image is used as an authenticated face image of the user, the identity card image is used as the authenticated image to prove that the identity of the user has higher credibility, and the definition and the face feature containing amount in the identity card image are generally higher than those of a common image.
In some optional implementations of this embodiment, the method shown in fig. 2 further includes: and in response to determining that the face image area is not contained in the image uploaded by the user, determining that the image uploaded by the user is a qualified image.
Specifically, if the user uploaded image does not include a face image region meeting a predetermined condition, it may be determined that the user uploaded image does not include a real face, and there is no infringement risk, so that the user uploaded image may be a qualified image, so as to implement quick judgment and verification of the user uploaded image, and improve the efficiency of the process.
In some optional implementations of this embodiment, the method shown above further includes: in response to determining that the similarity does not satisfy a predetermined threshold condition, determining the image on the user as a non-compliant image.
Specifically, when it is determined that the similarity between the face feature information included in the face image area in the user upload image and the face feature information included in the authenticated face image of the user does not satisfy the predetermined threshold condition, that is, the real face included in the user upload image does not belong to the user himself, the user is considered to use a photograph of another person, and the user upload image is an unqualified image. The classification of the user uploaded images is realized, and the subsequent platform can prohibit the user from using the images which are verified as being unqualified, so that the infringement risk is reduced.
In some optional implementations of this embodiment, the method shown above further includes: and in response to the fact that the face feature information contained in at least one face image area does not meet the preset screening requirement, additionally marking the image uploaded by the user as an uncertain image.
Specifically, if a face region exists in the user uploaded image, where the face feature information does not meet the preset screening requirement, it is determined that the real face region exists in the user uploaded image, but the region cannot be accurately analyzed. For example, there are a plurality of face regions satisfying a predetermined condition, but there are face regions whose face feature information does not support similarity determination, and it is not possible to determine all face regions satisfying the predetermined condition, or there is only one face region satisfying the predetermined condition but the face feature information does not support similarity determination as well. In the above situation, the result is inaccurate no matter whether the user uploaded images are unqualified images or not verified, and in order to improve the accuracy and rigor of verification, an additional uncertain mark is introduced, so that the part of the user uploaded images can be examined and rechecked in other ways in the following process.
Illustratively, in a specific application scenario, a user uploads a photo of a friend, when an image uploaded by the user is detected, two face image regions meeting a predetermined condition are determined, and at this time, if face feature information contained in the face image region corresponding to the user meets a predetermined screening requirement, the uploaded image a is verified as a qualified image, which is accurate. However, when the face feature information included in the face image region corresponding to the user does not satisfy the preset screening requirement, the image uploaded by the user is verified based on whether the face feature information included in the face image region corresponding to the friend satisfies the preset screening requirement, and in this case, the image is not verified accurately whether the image is verified as an unqualified image or not.
Therefore, an uncertain mark is additionally introduced to the condition, and the image is audited manually by a subsequent utility so as to ensure the accuracy of the audit.
In order to deepen understanding, the application also provides a specific implementation scheme by combining with a specific application scene, and in the practical application scene, a user A uploads a co-shooting image C of a partner B to be used as a head portrait.
After the execution main body acquires the image C, two face image areas are determined according to the pixels of the suspected face in the image C, whether the face confidence coefficient in the pixels of the face contained in the two face image areas is greater than or equal to 0.9 or not and the total pixel values of the width and the height of the picture, which are greater than 10% of the pixel value occupied by the maximum width and the maximum height of the face, are respectively analyzed, and the two face image areas in the image C are determined to meet the two predetermined conditions.
And detecting whether the face feature information contained in the two face image areas in the image C meets the preset screening requirements that the image shielding ratio is less than 0.5 and the blurring ratio is less than 0.5, and determining that the face image areas in the image C meet the two preset screening requirements.
And acquiring an identity card photo D uploaded by a user, and extracting the human face features in the identity card photo D by using a pre-trained extraction neural network.
And respectively calculating the similarity between the face features contained in the two face regions in the image C and the face features in the identification card photo D to obtain threshold conditions that the similarity is 90% and 43%, wherein the similarity 90% exceeds a preset 60%, so that the face contained in the face region in the image C is determined to be highly similar to the face contained in the identification card photo D, and the face can be considered as the same person.
And (4) verifying the image C as a qualified image, namely determining that the face image of the nail exists in the image C, and allowing the nail to use the image C as a head portrait.
According to the process for verifying the image shown in the specific application scene, after the image C uploaded by the first user is obtained, whether a human face image area meeting a predetermined condition exists in the image C is analyzed, a human face image area meeting the predetermined condition is obtained, whether the obtained human face image area meets a preset screening requirement is detected, human face features in the human face image meeting the preset screening requirement are compared with an authenticated image (identity card photo D) uploaded by the first user, a real human face of the first user is determined to be contained in the image C, the first user is allowed to use the image C as a head portrait without the risk of portrait infringement, and efficient head portrait auditing is completed.
Further, in order to deepen understanding, the application also provides an implementation scheme under another specific condition by combining a specific application scene, and in the actual application scene, the user C uploads a self-portrait image E of other users.
After the execution main body acquires the image E, two face image areas are determined according to the pixels of the suspected face in the image E, whether the face confidence coefficient in the pixels of the face contained in the face image areas is greater than or equal to 0.9 or not and the total pixel values of the width and the height of the picture, which are greater than 10% of the pixel values occupied by the maximum width and the maximum height of the face, are respectively analyzed, and it is determined that the two face image areas in the image D meet the two predetermined conditions.
Whether the face feature information contained in the two face image areas of the detector meets the preset screening requirements that the image shielding ratio is less than 0.5 and the blurring ratio is less than 0.5 or not is determined, and only one face image area meets the two preset screening requirements is determined.
And acquiring an identity card picture F uploaded by a user, and extracting the face features in the identity card picture F by using a pre-trained extraction neural network.
And calculating the similarity between the face features contained in the face region in the image E and the face features in the identification card picture F to obtain a threshold condition that the similarity is 43% and does not exceed the preset 60%, so that the face contained in the face region in the image E is determined to be not similar to the face contained in the identification card picture F and cannot be considered as the same person.
And (3) verifying the image E as an unqualified image, namely determining that the human face image of the third person exists in the image E, not allowing the image E to be used as a head portrait, and because a human face image area which does not meet the preset screening condition exists in the image E, additionally marking the image as an uncertain image so as to be used for reviewing the image in other ways later.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present application provides an embodiment of an apparatus for authenticating an image, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable in various electronic devices.
As shown in fig. 5, the apparatus 500 for verifying an image of the present embodiment may include: an image obtaining unit 501 configured to obtain a user upload image, and analyze whether the user upload image includes a face image region that satisfies a predetermined condition; an image screening unit 502 configured to detect whether the facial feature information included in the facial image region meets a preset screening requirement in response to determining that the user uploaded image includes at least one facial image region; an image comparison unit 503 configured to, in response to determining that the face feature information meets a preset screening requirement, obtain an authenticated face image of the user, and calculate a similarity between the face feature information included in the face image region and the face feature information included in the authenticated face image; a first image verification unit 504 configured to, in response to determining that the similarity satisfies a preset threshold condition, determine the user uploaded image as a qualified image.
In the present embodiment, it is used in the authentication image apparatus 500 to: the detailed processing and the technical effects of the image obtaining unit 501, the image screening unit 502, the image comparing unit 503 and the first image verifying unit 504 can refer to the related descriptions of step 201 and step 204 in the corresponding embodiment of fig. 2, and are not described herein again.
In some optional implementations of the present embodiment, the acquiring step of the authenticated face image in the image comparing unit 503 includes: acquiring an identity card image of the user, and extracting face feature information contained in the identity card image of the user by adopting a pre-trained extraction neural network; and in response to the result of the feature extraction meeting the predetermined credibility threshold requirement, taking the face image contained in the identity card image as the authenticated face image of the user.
In some optional implementations of the present embodiment, the predetermined condition in the image acquisition unit 501 includes at least one of: the face confidence, the non-cartoon confidence, the race confidence, the maximum width and height value of the face and the maximum width and height value of the face pixel in the face image region meet the corresponding threshold conditions.
In some optional implementations of the present embodiment, the preset screening requirement of the image screening unit 502 includes at least one of the following: the shielding proportion and the fuzzy proportion in the image of the face in the face image area, the vertical and horizontal angles of the three-dimensional rotation angle, the degree of confidence of the sunglasses meet the respective corresponding threshold conditions, and both eyes are in a non-closed state.
In some optional implementations of this embodiment, the apparatus shown above further includes: and the second verification image unit is configured to respond to the fact that the face image area meeting the predetermined condition is not contained in the user uploading image, and the user uploading image is a qualified image.
In some optional implementations of this embodiment, the apparatus shown above further includes: a third verification image unit configured to upload the user image as a non-compliant image in response to determining that the similarity does not satisfy a predetermined threshold condition.
In some optional implementations of this embodiment, the apparatus shown above further includes: and the image verification unit is configured to respond to the fact that the face feature information contained in at least one face image area does not meet the preset screening requirement, and additionally mark the image uploaded by the user as an uncertain image.
The present embodiment exists as an apparatus embodiment corresponding to the above method embodiment, and the same contents refer to the description of the above method embodiment, which is not repeated herein. The device for verifying the image provided by the embodiment of the application can verify the image uploaded by the user so as to improve the auditing efficiency.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 6, is a block diagram of an electronic device for a method of authenticating an image according to an embodiment of the present application. 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 present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method for authenticating an image provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method for authenticating an image provided by the present application.
The memory 602, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for verifying an image in the embodiments of the present application (for example, the image acquisition unit 501, the image filtering unit 502, the image comparison unit 503, and the first verification image unit 504 shown in fig. 5). The processor 601 executes various functional applications of the server and data processing, i.e., implements the method for authenticating an image in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 602.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device that pushes the information, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 may optionally include memory located remotely from the processor 601, which may be connected to an electronic device that pushes information over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device for the method of verifying an image may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic apparatus for verifying images, such as an input device like a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, etc. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), 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.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
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), and the Internet.
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.
According to the technical scheme of the embodiment of the application, when the information pushed to the user is generated, the generated pushed information is richer in content and more targeted.
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 the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. 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 application shall be included in the protection scope of the present application.
Claims (16)
1. A method for authenticating an image, comprising:
acquiring a user uploading image, and analyzing whether the user uploading image contains a face image area meeting a predetermined condition;
responding to the fact that at least one face image area is contained in the user uploaded image, and detecting whether face feature information contained in the face image area meets preset screening requirements or not;
in response to the fact that the face feature information meets the preset screening requirement, an authenticated face image of the user is obtained, and the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image is calculated;
and in response to the fact that the similarity meets a preset threshold condition, determining that the image uploaded by the user is a qualified image.
2. The method of claim 1, wherein the obtaining of the authenticated face image of the user comprises:
acquiring an identity card image of the user, and extracting face feature information contained in the identity card image of the user by adopting a pre-trained extraction neural network;
and in response to the fact that the extracted face feature information meets the requirement of a predetermined credibility threshold, taking a face image contained in the identity card image as an authenticated face image of the user.
3. The method of claim 1, wherein the predetermined condition comprises at least one of:
the face confidence, the non-cartoon confidence, the race confidence, the maximum face width and height value pixel value and the maximum face width and height value ratio of the face image region meet respective corresponding threshold conditions.
4. The method of claim 1, wherein the pre-set screening requirements comprise at least one of:
the shielding proportion and the fuzzy proportion in the image of the face in the face image area, the vertical and horizontal angles of the three-dimensional rotation angle, the degree of confidence of the sunglasses meet the respective corresponding threshold conditions, and both eyes are in a non-closed state.
5. The method of claim 1, further comprising:
and determining the user uploaded image as a qualified image in response to determining that the face image region meeting the predetermined condition is not included in the user uploaded image.
6. The method of claim 1, further comprising:
and in response to determining that the similarity does not meet a predetermined threshold condition, determining that the user uploaded image is a non-compliant image.
7. The method of any of claims 1-6, further comprising:
and in response to the fact that the face feature information contained in at least one face image area does not meet the preset screening requirement, additionally marking the images uploaded by the user as uncertain images.
8. An apparatus for authenticating an image, comprising:
the image acquisition unit is configured to acquire a user uploading image and analyze whether the user uploading image contains a face image area meeting a predetermined condition;
the image screening unit is configured to respond to the fact that at least one face image area is contained in the user uploading image, and detect whether face feature information contained in the face image area meets the preset screening requirement or not;
the image comparison unit is configured to respond to the fact that the face feature information meets the preset screening requirement, obtain an authenticated face image of the user, and calculate the similarity between the face feature information contained in the face image area and the face feature information contained in the authenticated face image;
a first verification image unit configured to determine that the user uploaded image is a qualified image in response to determining that the similarity satisfies a preset threshold condition.
9. The apparatus of claim 8, wherein the obtaining of the authenticated face image of the user in the image comparison unit comprises:
acquiring an identity card image of the user, and extracting face feature information contained in the identity card image of the user by adopting a pre-trained extraction neural network;
and in response to the fact that the extracted face feature information meets the requirement of a predetermined credibility threshold, taking a face image contained in the identity card image as an authenticated face image of the user.
10. The apparatus of claim 8, wherein the predetermined condition in the image acquisition unit comprises at least one of:
the face confidence, the non-cartoon confidence, the race confidence, the maximum face width and height value pixel value and the maximum face width and height value ratio of the face image region meet respective corresponding threshold conditions.
11. The apparatus according to claim 8, wherein in the image filtering unit, the preset filtering requirement includes at least one of:
the shielding proportion and the fuzzy proportion in the image of the face in the face image area, the vertical and horizontal angles of the three-dimensional rotation angle, the degree of confidence of the sunglasses meet the respective corresponding threshold conditions, and both eyes are in a non-closed state.
12. The apparatus of claim 8, further comprising:
a second verification image unit configured to determine that the user upload image is an unqualified image in response to determining that the face image region satisfying the predetermined condition is not included in the user upload image.
13. The apparatus of claim 8, further comprising:
a third verification image unit configured to determine that the user uploaded image is a qualified image in response to determining that the similarity does not satisfy a predetermined threshold condition.
14. The apparatus of any of claims 8-13, further comprising:
and the image marking unit is configured to additionally mark the image uploaded by the user as an uncertain image in response to the fact that the face feature information contained in at least one face image area does not meet the preset screening requirement.
15. 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 of any one of claims 1-7.
16. A non-transitory computer readable storage medium storing computer instructions, comprising: the computer instructions are for causing the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010603371.4A CN111767840A (en) | 2020-06-29 | 2020-06-29 | Method, apparatus, electronic device and computer-readable storage medium for verifying image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010603371.4A CN111767840A (en) | 2020-06-29 | 2020-06-29 | Method, apparatus, electronic device and computer-readable storage medium for verifying image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111767840A true CN111767840A (en) | 2020-10-13 |
Family
ID=72722857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010603371.4A Pending CN111767840A (en) | 2020-06-29 | 2020-06-29 | Method, apparatus, electronic device and computer-readable storage medium for verifying image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111767840A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765487A (en) * | 2021-01-25 | 2021-05-07 | 深圳市爱聊科技有限公司 | Interaction method, interaction device, electronic equipment and computer storage medium |
| CN113057529A (en) * | 2021-02-22 | 2021-07-02 | 江苏柯林博特智能科技有限公司 | Garbage classification control system based on stair cleaning robot |
| CN113836466A (en) * | 2021-09-18 | 2021-12-24 | 北京来也网络科技有限公司 | Method and device for pushing station internal information based on RPA and AI and computing equipment |
| CN117455634A (en) * | 2023-10-27 | 2024-01-26 | 浪潮智慧科技有限公司 | Rental management and control method, equipment and medium for agricultural equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015051657A1 (en) * | 2013-10-12 | 2015-04-16 | 腾讯科技（深圳）有限公司 | User search method and device |
| CN106530185A (en) * | 2016-11-11 | 2017-03-22 | 深圳前海微众银行股份有限公司 | Identity authentication-based business processing method and system, and identity authentication platform |
| CN109359508A (en) * | 2018-08-27 | 2019-02-19 | 贵阳朗玛信息技术股份有限公司 | A kind of head portrait processing method and processing device |
| CN109409245A (en) * | 2018-09-30 | 2019-03-01 | 江苏满运软件科技有限公司 | Identity checking method, system, electronic equipment and storage medium |
| WO2019104930A1 (en) * | 2017-12-01 | 2019-06-06 | 平安科技（深圳）有限公司 | Identity authentication method, electronic device and computer-readable storage medium |
| CN110795714A (en) * | 2019-09-10 | 2020-02-14 | 中国平安财产保险股份有限公司 | Identity authentication method and device, computer equipment and storage medium |
| WO2020062783A1 (en) * | 2018-09-29 | 2020-04-02 | 深圳壹账通智能科技有限公司 | Identity authentication method and apparatus, and terminal device and storage medium |
-
2020
- 2020-06-29 CN CN202010603371.4A patent/CN111767840A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015051657A1 (en) * | 2013-10-12 | 2015-04-16 | 腾讯科技（深圳）有限公司 | User search method and device |
| CN106530185A (en) * | 2016-11-11 | 2017-03-22 | 深圳前海微众银行股份有限公司 | Identity authentication-based business processing method and system, and identity authentication platform |
| WO2019104930A1 (en) * | 2017-12-01 | 2019-06-06 | 平安科技（深圳）有限公司 | Identity authentication method, electronic device and computer-readable storage medium |
| CN109359508A (en) * | 2018-08-27 | 2019-02-19 | 贵阳朗玛信息技术股份有限公司 | A kind of head portrait processing method and processing device |
| WO2020062783A1 (en) * | 2018-09-29 | 2020-04-02 | 深圳壹账通智能科技有限公司 | Identity authentication method and apparatus, and terminal device and storage medium |
| CN109409245A (en) * | 2018-09-30 | 2019-03-01 | 江苏满运软件科技有限公司 | Identity checking method, system, electronic equipment and storage medium |
| CN110795714A (en) * | 2019-09-10 | 2020-02-14 | 中国平安财产保险股份有限公司 | Identity authentication method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 方圆圆: "《人脸识别与美颜算法实战 基于Python、机器学习与深度学习》", 30 April 2020, 机械工业出版社, pages: 113 - 114 * |
| 韩睿;: "基于深度学习的人脸识别系统", 电子技术与软件工程, no. 10 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765487A (en) * | 2021-01-25 | 2021-05-07 | 深圳市爱聊科技有限公司 | Interaction method, interaction device, electronic equipment and computer storage medium |
| CN113057529A (en) * | 2021-02-22 | 2021-07-02 | 江苏柯林博特智能科技有限公司 | Garbage classification control system based on stair cleaning robot |
| CN113836466A (en) * | 2021-09-18 | 2021-12-24 | 北京来也网络科技有限公司 | Method and device for pushing station internal information based on RPA and AI and computing equipment |
| CN117455634A (en) * | 2023-10-27 | 2024-01-26 | 浪潮智慧科技有限公司 | Rental management and control method, equipment and medium for agricultural equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767840A (en) | Method, apparatus, electronic device and computer-readable storage medium for verifying image | |
| CN111886842B (en) | Remote user authentication using threshold-based matching | |
| US10074008B2 (en) | Facial recognition with biometric pre-filters | |
| Li et al. | Understanding OSN-based facial disclosure against face authentication systems | |
| US8995775B2 (en) | Reducing photo-tagging spam | |
| US11048919B1 (en) | Person tracking across video instances | |
| CN111753701B (en) | Method, device, equipment and readable storage medium for detecting violation of application program | |
| CN107615288B (en) | Gesture matching mechanism | |
| WO2022068320A1 (en) | Computer automated interactive activity recognition based on keypoint detection | |
| WO2016084072A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| US20190347472A1 (en) | Method and system for image identification | |
| CN111898561B (en) | Face authentication method, device, equipment and medium | |
| EP2701096A2 (en) | Image processing device and image processing method | |
| JP2018116589A (en) | State identification apparatus, program, and method using changed image group of target images | |
| CN110276313B (en) | Identity authentication method, identity authentication device, medium and computing equipment | |
| CN108875582A (en) | Auth method, device, equipment, storage medium and program | |
| CN111783639A (en) | Image detection method and device, electronic equipment and readable storage medium | |
| CN111738199B (en) | Image information verification method, device, computing device and medium | |
| US11087121B2 (en) | High accuracy and volume facial recognition on mobile platforms | |
| US11538283B1 (en) | Detecting people wearing masks to prevent impersonation attacks | |
| CN111552829B (en) | Method and apparatus for analyzing image material | |
| CN111368128B (en) | Target picture identification method, device and computer readable storage medium | |
| US11763604B2 (en) | Liveness detection based on reflections analysis | |
| CN112949467A (en) | Face detection method and device, electronic equipment and storage medium | |
| CN109242489B (en) | Authentication mode selection method and device |
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 |