CN110826460B - Abnormal testimony of a witness information identification method, device and storage medium - Google Patents
Abnormal testimony of a witness information identification method, device and storage medium Download PDFInfo
- Publication number
- CN110826460B CN110826460B CN201911051310.5A CN201911051310A CN110826460B CN 110826460 B CN110826460 B CN 110826460B CN 201911051310 A CN201911051310 A CN 201911051310A CN 110826460 B CN110826460 B CN 110826460B
- Authority
- CN
- China
- Prior art keywords
- information
- portrait
- face
- certificate
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012795 verification Methods 0.000 claims abstract description 47
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 3
- 230000002547 anomalous effect Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 abstract description 18
- 239000013598 vector Substances 0.000 description 32
- 230000000694 effects Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000000605 extraction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- 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
- 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)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to an abnormal testimony of a witness information identification method, a device and a storage medium. The method comprises the following steps: acquiring collected information from a human certificate verification device, wherein the collected information comprises face information and certificate information; clustering multiple groups of the collected information according to the face information in the collected information to obtain a face file; and when a plurality of different certificate information are associated in the same portrait archive, generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive. According to the technical scheme, illegal behaviors such as one person for more evidences can be timely and accurately found through the acquired information of the people evidence verification equipment.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an abnormal testimony of a witness information identification method, an abnormal testimony of a witness information identification device and a storage medium.
Background
Along with the continuously increasing public security control requirements, more and more testimony of a witness verification devices are arranged at places such as entertainment places, hotels, internet cafes and transportation hubs, for example, an integrated testimony of a witness verification machine, an identity card reader, a combination of a face image acquisition camera and the like, a testimony of a witness verification system covering a public area is gradually constructed, testimony of a witness information verification can be carried out on personnel entering key places, one person can be guaranteed to be certified, and the personnel can be given a new name. Meanwhile, in the scenes of needing to verify the identity of the personnel, such as a government service window, a bank window and the like, the personnel identity verification equipment is also arranged so as to automatically and accurately realize the personnel identity verification and confirm the real identity of the serviced personnel.
The current people's card verification system realizes face snapshot and identity card swiping and reading operations simultaneously by the verified personnel staying in front of the people's card verification equipment, and then verifies the snapshot portrait and the corresponding identity card information. For personnel without identity cards, the personnel card verification equipment can be connected with the rear-end platform and guided into the population library for comparison, so that the personnel card information verification is realized. However, even if the comparison is performed through the associated population database, personnel can handle a plurality of identity cards through various channels, and the method has potential social hazard. At present, the information collected by the human authentication and verification equipment is only subjected to human authentication and comparison, and the collected information is not further analyzed and mined.
Disclosure of Invention
The invention provides an abnormal testimony information identification method, an abnormal testimony information identification device and a storage medium, which aim to accurately find illegal behaviors such as one person with multiple testimonies in testimony information verification.
In a first aspect, the present invention provides a method for identifying abnormal testimony information, which comprises the following steps:
acquiring collected information from a human certificate verification device, wherein the collected information comprises face information and certificate information;
clustering multiple groups of the collected information according to the face information in the collected information to obtain a face file;
and when a plurality of different certificate information are associated in the same portrait archive, generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive.
In a second aspect, the present invention provides an abnormal testimony of a witness information recognition apparatus, comprising:
the system comprises an acquisition module, a verification module and a verification module, wherein the acquisition module is used for acquiring acquisition information from a human face verification device, and the acquisition information comprises human face information and certificate information;
the processing module is used for clustering a plurality of groups of the acquired information according to the face information in the acquired information to obtain a face file;
and the generation module is used for generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive when the same portrait archive is associated with a plurality of different certificate information.
In a third aspect, the present invention provides an abnormal testimonial information identification apparatus, comprising a memory and a processor; the memory for storing a computer program; the processor is used for realizing the abnormal testimony information identification method when the computer program is executed.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the abnormal testimony information identification method as described above.
The method, the device and the storage medium for identifying the abnormal testimony information have the advantages that information acquisition can be carried out through testimony verification equipment arranged at each position, and a plurality of groups of acquired information including face information and certificate information are obtained. By adopting a clustering method, the face information with higher similarity and the certificate information corresponding to the face information can be classified into a portrait file. Because the portrait file is associated with the certificate information which is in the same acquisition information with the face information, if a plurality of certificate information are associated with the same portrait file, it is indicated that a person corresponding to the portrait file may have a behavior of one person for multiple certificates, and at this time, abnormal early warning information of one person for multiple certificates can be generated for the portrait file or for the person, and a related management department can further check or investigate the person in time according to the abnormal early warning information to prevent further illegal behaviors of the person. Through further analysis and mining of the collected information of the personal authentication and verification equipment, illegal behaviors such as one person with multiple certificates and the like can be timely and accurately found, and the accuracy and the comprehensiveness of social security management are ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of an abnormal testimony of witness information identification method according to an embodiment of the present invention;
fig. 2 is a block diagram of an abnormal testimony information recognition apparatus according to an embodiment of the present invention;
fig. 3 is a block diagram of an abnormal testimony of a witness information identification system according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the method for identifying abnormal testimony information according to the embodiment of the present invention includes the following steps:
s1, acquiring acquisition information from a people certificate verification device, wherein the acquisition information comprises face information and certificate information.
Specifically, information acquisition can be performed through the people's identity card verification equipment arranged at each position, and multiple groups of acquisition information including face information and certificate information are obtained, wherein the face information can be a person snapshot image or a feature vector extracted according to the person snapshot image, and the certificate information can be information with unique identification such as identity card information, passport information or driving license information.
In addition, part of the human evidence verification equipment has the function of extracting the human image features, namely, the human image snapshot image can be subjected to feature extraction, and the extracted feature vectors can be used as the human face information. If the same feature extraction algorithm is adopted by each witness verification device or the extracted feature vectors meet the same standard, the feature vectors can be used as face information and sent to a background server together with certificate information, namely the abnormal witness information identification device in the application, so that the processing pressure of the background server is reduced. If each person certificate verification device adopts different feature extraction algorithms or the extracted feature vectors do not accord with the same standard, the portrait snapshot image can be directly taken as face information and sent to a background server together with certificate information, namely the abnormal person certificate information identification device in the application.
And S2, clustering multiple groups of collected information according to the face information in the collected information to obtain a face file.
Specifically, the collected information may be information collected and sent by the same human authentication device in different time periods, or information collected and sent by different human authentication devices in the same time period, which generally has a larger data size. Different pieces of collected information are subjected to cluster analysis based on the face information in the pieces of collected information, and at the moment, the pieces of collected information corresponding to the face information with the distance smaller than the distance threshold value are clustered into one type, so that face information pointing to different faces, more specifically, face files pointing to different people can be obtained.
And S3, when a plurality of different certificate information are associated in the same portrait archive, generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive.
Specifically, the portrait archive includes face information whose distance is smaller than a distance threshold value at the time of clustering, and is associated with certificate information located in the same collected information as the face information. If it is confirmed that the same portrait file is associated with a plurality of different certificate information, it is indicated that although a plurality of face information in the portrait file may point to the same person, the person may hold a plurality of certificates of the same type, i.e. the person may have one person and a plurality of certificates. At this time, one-person multi-evidence abnormal early warning information can be generated for the portrait archive or the personnel. As shown in fig. 3, at this time, the backend server, that is, the abnormal witness information identification device in the present application, may send the one-person multi-witness abnormal early warning information to a terminal of a relevant management department, for example, a terminal of a public security management department, and the relevant department may further check or investigate the person in time according to the abnormal early warning information.
In this embodiment, the collected information including the portrait information and the certificate information acquired by the people and certificate verification device is used to respectively establish portrait files for different people through a clustering analysis method, and the comparison of the portrait files is used to find whether a specific person has illegal behaviors such as one person with multiple certificates and the like, so as to ensure the accuracy and the safety of social security management.
Optionally, the clustering, according to the face information in the collected information, the multiple groups of the collected information to obtain a face archive includes:
when the similarity between the face information in at least two groups of the collected information is larger than a preset threshold value, classifying the at least two groups of the face information into a portrait archive, and associating the portrait archive with the certificate information in the at least two groups of the collected information.
Specifically, if the face information is a face feature vector extracted in advance by the face verification device, the face features do not need to be extracted again; if the face information is a portrait snapshot, face features need to be extracted first to obtain face feature vectors, and then clustering is performed according to the face feature vectors.
In the embodiment, based on the portrait clustering technology, a plurality of portrait archives respectively corresponding to different personnel are established, and when abnormal portrait evidence information identification is performed, the acquisition information matched with the specific portrait archives can be quickly and accurately identified, so that whether one person exists or not can be quickly determined, and the following management work can be conveniently and effectively carried out.
Optionally, the method further comprises the steps of:
and comparing the face information in the subsequent acquisition information acquired after clustering with the acquired archive face information of the portrait archive respectively, filing the face information into the calibrated portrait archive when the similarity between the face information in the subsequent acquisition information and the archive face information of the calibrated portrait archive in the acquired portrait archive is greater than a preset threshold value, and associating the calibrated portrait archive with certificate information in the subsequent acquisition information.
Specifically, through clustering, a plurality of initial portrait files are established, and then the face information can be directly compared with the file portrait information of each initial portrait file in the feature comparison of the acquired subsequent acquisition information.
More specifically, taking the face information in the subsequent collected information as a snapshot of the portrait as an example, feature extraction is performed on the snapshot of the portrait to obtain a feature vector of the snapshot of the portrait. Correspondingly, the archive face information of each person archive may also be in the form of a feature vector, and at this time, the feature vector of the archive face information may be referred to as an archive feature vector, and the archive feature vector of each person archive may be information generated in the above-mentioned clustering process, or information obtained by further updating in the following process.
Then, the extracted feature vectors are respectively compared with the file feature vectors of the existing portrait files, and the similarity between the extracted feature vectors and the file feature vectors is determined. The similarity is the similarity between the face information in the subsequent collected information and the face information of the file of the calibration portrait file in the acquired portrait file.
In the clustering process, at least two groups of collected information, namely at least two portrait capture images, are obtained, firstly, feature extraction is carried out on the portrait capture images to obtain feature vectors, the similarity between different portrait capture images is determined according to the feature vectors, and when the similarity is larger than a preset threshold value, the fact that personnel corresponding to the at least two portrait capture images are the same person is indicated. In this case, the at least two portrait shots are aggregated into one portrait file corresponding to the person, and the feature vectors of the at least two portrait shots are fused, and more specifically, for example, the first portrait shot has 128 feature points, the second portrait shot also has 128 feature points, and the parameters of the corresponding feature points are weighted and averaged to form the file feature vector of the portrait file. Certainly, the file feature vector of the portrait file can also directly adopt the feature vector of the portrait snapshot image with better definition and angle. Meanwhile, certificate information in the collected information is associated with the portrait file. That is, one portrait archive includes archive face information constituted by at least two portrait snapshots and certificate information corresponding to the portrait snapshots, and the archive feature vectors are generated according to the portrait snapshots.
And when the similarity is greater than a preset threshold value, filing the face information into a calibration portrait file, and associating the calibration portrait file with certificate information in the acquisition information. Because the calibration portrait file is associated with certificate information at the moment, when the certificate information is confirmed to be different from other certificate information associated with the calibration portrait file, one-person multi-certificate abnormal early warning information can be generated aiming at the calibration portrait file at the moment.
In the embodiment, the collected information is filed in real time and further analyzed, and the instantaneity of identification of the abnormal testimony information can be effectively ensured.
Optionally, the method further comprises the steps of:
in response to archiving the face information into the calibration portrait archive, generating updated archive face information for the calibration portrait archive according to the face information and archive face information for the calibration portrait archive; the updated profile face information of the calibration portrait profile is used to compare with the acquisition information obtained after generating the updated profile face information of the calibration portrait profile.
Specifically, continuing to take the face information as the snapshot as an example, when a certain snapshot is filed into a matching portrait file, the face information of the file of the portrait file, or the file feature vector of the portrait file, needs to be updated. At this time, the face image file adds new face information filed in the face image file on the basis of the original face information to generate updated face information of the file. The change of the face information of the file is mainly embodied in the change of the file feature vector, for example, the feature vector of the portrait snapshot image can be firstly extracted, and then the feature vector and the existing file feature vector of the portrait file are subjected to feature fusion calculation to obtain an updated file feature vector, or the feature vector of the picture with the highest quality in the portrait file including the portrait snapshot image is directly selected as the updated file feature vector.
In the embodiment, the face information matched with the face file is used for updating the face information of the file of the face file, so that the comparison result of the collected information and the face file can be more accurate in the subsequent information collection and comparison process, and the accuracy of identification of the abnormal testimony information is ensured.
In addition, all the personnel may not be covered in the early stage of the clustering process, so that the portrait files of only part of the personnel are generated at the moment, and the portrait files of other personnel can be continuously established in a clustering mode when subsequent acquisition information is obtained. For example, if face information matched with face information in a certain group of collected information or acquired archival face information of a portrait archive is not found, the subsequent face information in the collected information which is not matched with any face information or archival face information of the portrait archive is waited, the face information in the two groups of collected information are compared, if the similarity between the two is greater than a preset threshold value, the corresponding people are the same person, and a new portrait archive can be established based on the two and used in the subsequent comparison process.
Optionally, the acquisition information further includes time information and/or location information. The method also includes the steps of:
and for the portrait files corresponding to the one-person multi-certificate abnormal early warning information, when acquiring face information of which the similarity of the face information of the archives corresponding to the one-person multi-certificate abnormal early warning information is larger than a preset threshold value again, determining the acquisition information corresponding to the face information, and generating alarm information according to the time information and/or the location information.
Specifically, if one-person multi-certificate abnormal early warning information is generated, it is indicated that a corresponding person may have one-person multi-certificate behaviors, the person may be considered as a suspicious person, when the person reappears in a specific field and is subjected to information acquisition by the person-certificate verification device at the specific field, for example, one-person multi-certificate abnormal early warning information is generated for a certain person, the person is found to be located at an airport exit-entry place again to be checked at present, at this time, alarm information can be generated, as shown in fig. 3, and the alarm information is accurately sent to a frontier inspection department terminal located at the exit-entry place by a background server, that is, the abnormal person-certificate information identification device in the present application according to, for example, location information of the device, and the like, so as to inform a relevant department to further verify the suspicious person, and avoid illegal person from escaping from the exit.
In this embodiment, after generating the one-person multi-evidence abnormal early warning information, if necessary, alarm information may be generated according to the current activity information of the person, more specifically, the suspected illegal activity information in the key area, and may be handed to a management department in the area for further verification and processing in time, so as to prevent potential illegal activities and ensure stable social security.
Optionally, the method further comprises the steps of:
and generating the personnel activity rule information of the face information corresponding to the portrait archive according to the time information and/or the place information for the portrait archive corresponding to the one-person-multiple-certificate abnormal early warning information.
Specifically, the information sent by the same people verification equipment at different time can have different time information, the information sent by different people verification equipment can have different place information and/or time information, and the information can reflect the space-time activity track of the collected information personnel. If one-person multi-evidence abnormal early warning information is generated, it is indicated that one-person multi-evidence behaviors may exist in corresponding personnel, the personnel can be regarded as suspicious personnel, as shown in fig. 3, a background server, that is, an abnormal personnel evidence information identification device in the application sends the one-person multi-evidence abnormal early warning information to, for example, a terminal of a public security management department, and the activity behaviors of the suspicious personnel can be analyzed according to time information and location information, for example, through places where the personnel frequently appear, such as hotels and internet cafes registered in, behavior rules of the suspicious personnel are researched and judged, and if illegal behaviors do exist, the behavior can be controlled in advance and caught.
In this embodiment, after the one-person multiple-evidence abnormal early warning information is generated, if necessary, the activity rule of the person can be further analyzed according to the portrait archive of the person, so that potential illegal behaviors are prevented, and the social security and safety are ensured.
Optionally, the method further comprises the steps of:
and when determining that a plurality of portrait archives are associated with the same certificate information, generating multi-person one-certificate abnormal early warning information.
Specifically, since a plurality of portrait files exist and each portrait file is associated with certificate information, if the certificate information associated with the plurality of portrait files is found to be the same certificate information, the multi-person one-certificate abnormality early warning information is generated. For example, when it is found that there are a plurality of portrait files corresponding to one identity number in the authentication data of banking institutions in different cities across the country, it is described that there may be a situation that the identity number of a certain person is stolen, attention needs to be focused, and a multi-person one-certificate abnormal early warning message is generated, as shown in fig. 3, the multi-person one-certificate abnormal early warning message is sent to a bank terminal by a background server, that is, the abnormal person authentication information identification device in the present application, so that a relevant management department can be prompted to check and process in time.
In this embodiment, by comparing a plurality of different portrait files, whether a possible situation of one card for a plurality of people exists can be determined, and one card for a plurality of people abnormal early warning information can be generated, so that the relevant management part can be assisted to discover illegal behaviors such as identity card embezzlement and the like in time and process the behaviors.
Optionally, the method further comprises the steps of:
and acquiring identity verification information corresponding to the certificate information according to the same certificate information associated with the portrait files, and verifying the portrait files according to the identity verification information.
In particular, in the case of a plurality of persons possibly, malicious behaviors that the identity card of a person is copied and faked can exist, and the identity card can be verified in a corresponding issuing place or a certificate registration place system according to the associated certificate information. For example, according to the associated identification card information, the affiliated place is determined, inquiry information is sent to the terminal of the public security management department corresponding to the affiliated place, and feedback information of the department is received, that is, identity verification information of which person the certificate information points to is determined, and further, according to the identity verification information, which person is a real person and which person is a suspected identity card embezzled person in a plurality of persons associated with the same certificate is determined. As shown in fig. 3, at this time, the identity verification information can be sent to a security management department terminal corresponding to the location of the suspected identity card embezzlement person by the background server, that is, the abnormal personal identification card information recognition device in the present application, and the security management department can further determine the activity rule of the suspected identity card embezzlement person according to the portrait file of the suspected identity card embezzlement person, and finally capture the person embezzled with the identity card of another person. In addition, for such personnel, whether the personnel still have behaviors such as one person for more certificates and the like can be further checked through the portrait archive of the personnel.
In the embodiment, after the one-card behavior of a plurality of persons is determined, the person can be verified in time, the real identity person and the information stealing person can be determined, and the information stealing person can be controlled and arrested according to the portrait file.
As shown in fig. 2, an abnormal testimony information identification apparatus according to an embodiment of the present invention includes:
the system comprises an acquisition module, a verification module and a verification module, wherein the acquisition module is used for acquiring acquisition information from a human face verification device, and the acquisition information comprises human face information and certificate information;
the processing module is used for clustering a plurality of groups of the acquired information according to the face information in the acquired information to obtain a face file;
and the generation module is used for generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive when the same portrait archive is associated with a plurality of different certificate information.
Optionally, the processing module is specifically configured to: when the similarity between the face information in at least two groups of the collected information is larger than a preset threshold value, classifying the at least two groups of the face information into a portrait archive, and associating the portrait archive with the certificate information in the at least two groups of the collected information.
Optionally, the processing module is further configured to: and comparing the face information in the subsequent acquisition information acquired after clustering with the acquired archive face information of the portrait archive respectively, filing the face information into the calibrated portrait archive when the similarity between the face information in the subsequent acquisition information and the archive face information of the calibrated portrait archive in the acquired portrait archive is greater than a preset threshold value, and associating the calibrated portrait archive with certificate information in the subsequent acquisition information.
Optionally, the processing module is further configured to: in response to archiving the face information into the calibration portrait archive, generating updated archive face information for the calibration portrait archive according to the face information and archive face information for the calibration portrait archive; the updated profile face information of the calibration portrait profile is used to compare with the acquisition information obtained after generating the updated profile face information of the calibration portrait profile.
Optionally, the acquisition information further includes time information and/or location information. The generation module is further to: and for the portrait file corresponding to the one-person multi-certificate abnormal early warning information, when the face information of which the similarity of the face information of the portrait file corresponding to the one-person multi-certificate abnormal early warning information is larger than a preset threshold value is acquired again, determining the acquisition information corresponding to the face information, and generating alarm information according to the time information and/or the location information.
Optionally, the generating module is further configured to: and when determining that a plurality of portrait archives are associated with the same certificate information, generating multi-person one-certificate abnormal early warning information.
Optionally, the processing module is further configured to: and acquiring identity verification information corresponding to the certificate information according to the same certificate information associated with the portrait files, and verifying the portrait files according to the identity verification information.
In another embodiment of the present invention, an abnormal testimonial information identification apparatus includes a memory and a processor. The memory is used for storing computer programs. The processor is used for realizing the abnormal testimony information identification method when the computer program is executed.
It should be noted that the device may be a computer device such as a server.
In another embodiment of the present invention, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the abnormal testimony information identification method as described above.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example" or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (9)
1. An abnormal testimony information identification method is characterized by comprising the following steps:
acquiring collected information from a human certificate verification device, wherein the collected information comprises face information and certificate information;
clustering multiple groups of the collected information according to the face information in the collected information to obtain a face file;
when a plurality of different certificate information are associated in the same portrait archive, generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive;
the clustering is performed on the multiple groups of the collected information according to the face information in the collected information to obtain a face file, and the clustering specifically comprises the following steps:
when the similarity between the face information in at least two groups of the collected information is larger than a preset threshold value, classifying the at least two groups of the face information into a portrait archive, and associating the portrait archive with the certificate information in the at least two groups of the collected information.
2. The method of identifying abnormal witness information of claim 1, further comprising:
and comparing the face information in the subsequent acquired information acquired after clustering with the acquired file face information of the portrait file, when the similarity between the face information in the subsequent acquired information and the file face information of the calibration portrait file in the acquired portrait file is greater than a preset threshold value, filing the face information into the calibration portrait file, and associating the calibration portrait file with the certificate information in the subsequent acquired information.
3. The method of identifying abnormal witness information of claim 2, further comprising:
in response to archiving the face information into the calibration portrait archive, generating updated archive face information for the calibration portrait archive according to the face information and archive face information for the calibration portrait archive; the updated profile face information of the calibration portrait profile is used to compare with the acquisition information obtained after generating the updated profile face information of the calibration portrait profile.
4. The abnormal testimony of a human being information identification method according to claim 1, wherein the collection information further includes time information and/or location information; the abnormal testimony information identification method further comprises the following steps:
and for the portrait files corresponding to the one-person multi-certificate abnormal early warning information, when acquiring face information of which the similarity of the face information of the archives corresponding to the one-person multi-certificate abnormal early warning information is larger than a preset threshold value again, determining the acquisition information corresponding to the face information, and generating alarm information according to the time information and/or the location information.
5. The abnormal testimony information identification method according to any one of claims 1 to 4, further comprising:
and when determining that a plurality of portrait archives are associated with the same certificate information, generating multi-person one-certificate abnormal early warning information.
6. The method of identifying anomalous witness information of claim 5, further comprising:
and acquiring identity verification information corresponding to the certificate information according to the same certificate information associated with the portrait files, and verifying the portrait files according to the identity verification information.
7. An abnormal testimony information recognition device, comprising:
the system comprises an acquisition module, a verification module and a verification module, wherein the acquisition module is used for acquiring acquisition information from a human face verification device, and the acquisition information comprises human face information and certificate information;
the processing module is used for clustering a plurality of groups of the collected information according to the face information in the collected information to obtain a face file; the method is specifically used for: when the similarity between the face information in at least two groups of the collected information in the multiple groups of the collected information is larger than a preset threshold value, classifying the at least two groups of the face information into a portrait file, and associating the portrait file with the certificate information in the at least two groups of the collected information;
and the generation module is used for generating one-person multi-certificate abnormal early warning information aiming at the same portrait archive when the same portrait archive is associated with a plurality of different certificate information.
8. An abnormal testimony information identification device is characterized by comprising a memory and a processor;
the memory for storing a computer program;
the processor, when executing the computer program, is configured to implement the method for identifying abnormal testimonial information according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when executed by a processor, implements the abnormal testimonial information identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911051310.5A CN110826460B (en) | 2019-10-31 | 2019-10-31 | Abnormal testimony of a witness information identification method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911051310.5A CN110826460B (en) | 2019-10-31 | 2019-10-31 | Abnormal testimony of a witness information identification method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110826460A CN110826460A (en) | 2020-02-21 |
| CN110826460B true CN110826460B (en) | 2023-04-18 |
Family
ID=69551591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911051310.5A Active CN110826460B (en) | 2019-10-31 | 2019-10-31 | Abnormal testimony of a witness information identification method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110826460B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114780711B (en) * | 2022-06-21 | 2022-09-16 | 广州卓腾科技有限公司 | Certificate application identification method, system and medium based on intelligent file platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867231A (en) * | 2012-08-22 | 2013-01-09 | 北京航天金盾科技有限公司 | Resident identification card accreditation system and method with image and fingerprint comparison functions |
| CN104134065A (en) * | 2014-07-11 | 2014-11-05 | 北京航天金盾科技有限公司 | Office business system with face comparison and fingerprint identification functions for notary office |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103188445A (en) * | 2013-02-16 | 2013-07-03 | 宝鸡市交通信息工程研究所 | Imaging method for automatically overlaying identity information to identification photo, special imaging system and immediate identity information updating method |
| CN204155328U (en) * | 2014-09-02 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | A kind of hand-held mobile personnel based on recognition of face registers checking device |
| CN105184255B (en) * | 2015-09-06 | 2018-09-11 | 天维尔信息科技股份有限公司 | The testimony of a witness veritifies device and certificate generating means |
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109902780A (en) * | 2019-02-14 | 2019-06-18 | 广州番禺职业技术学院 | Testimony of a witness unification verification terminal and system and method based on multi-modal recognition of face |
-
2019
- 2019-10-31 CN CN201911051310.5A patent/CN110826460B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867231A (en) * | 2012-08-22 | 2013-01-09 | 北京航天金盾科技有限公司 | Resident identification card accreditation system and method with image and fingerprint comparison functions |
| CN104134065A (en) * | 2014-07-11 | 2014-11-05 | 北京航天金盾科技有限公司 | Office business system with face comparison and fingerprint identification functions for notary office |
Non-Patent Citations (1)
| Title |
|---|
| 王凯.人证合一在机场安检系统中的应用.《智能建筑》.2018,(第11期),第59-61页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110826460A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sharma et al. | Reliable biometric authentication with privacy protection | |
| US20210334571A1 (en) | System for multiple algorithm processing of biometric data | |
| US9704051B2 (en) | Method and system for verifying identities | |
| CN109948408B (en) | Activity test method and apparatus | |
| JP6464338B2 (en) | Evidence to protect privacy in ALPR applications | |
| EP3005202B1 (en) | System and method for biometric authentication with device attestation | |
| EP3407232B1 (en) | Spatiotemporal authentication | |
| CN108875341A (en) | A kind of face unlocking method, device, system and computer storage medium | |
| US20210006558A1 (en) | Method, apparatus and system for performing authentication using face recognition | |
| WO2010001311A1 (en) | Networked face recognition system | |
| Berle et al. | What is face recognition technology? | |
| US11716330B2 (en) | Mobile enrollment using a known biometric | |
| CN108959884B (en) | Human authentication verification device and method | |
| Mane et al. | Review of multimodal biometrics: applications, challenges and research areas | |
| CN103646200B (en) | The coding encrypting of a kind of face information and application process | |
| KR101957677B1 (en) | System for learning based real time guidance through face recognition and the method thereof | |
| KR102188775B1 (en) | Method and system for remotely controlling client terminals using face recognition and face recognition terminal | |
| CN110826460B (en) | Abnormal testimony of a witness information identification method, device and storage medium | |
| CN111932270A (en) | Method and device for bank customer identity verification | |
| CN112183161A (en) | Method, device and equipment for processing face database | |
| CN116070185A (en) | System and method for processing data body rights requests using biometric data matching | |
| CN114297612A (en) | Authentication method, system and device based on improved cryptographic algorithm | |
| KR102069567B1 (en) | Structured Cabling System Using Biometric Authentication | |
| US20200364321A1 (en) | Method and apparatus for providing authentication using voice and facial data | |
| CN106157412A (en) | A kind of personnel's access system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230818 Address after: No. 1268, 1f, building 12, neijian Middle Road, Xisanqi building materials City, Haidian District, Beijing 100096 Patentee after: BEIJING KUANGSHI TECHNOLOGY Co.,Ltd. Address before: 100080 room 1018, 10th floor, 1 Zhongguancun Street, Haidian District, Beijing Patentee before: BEIJING KUANGSHI TECHNOLOGY Co.,Ltd. Patentee before: Qingdao Guangshi Technology Co.,Ltd. |