CN105184932A - Method and device for recognizing persons through intelligent access control machine - Google Patents
Method and device for recognizing persons through intelligent access control machine Download PDFInfo
- Publication number
- CN105184932A CN105184932A CN201510644835.5A CN201510644835A CN105184932A CN 105184932 A CN105184932 A CN 105184932A CN 201510644835 A CN201510644835 A CN 201510644835A CN 105184932 A CN105184932 A CN 105184932A
- Authority
- CN
- China
- Prior art keywords
- information
- entrance guard
- intelligent entrance
- training sample
- guard machine
- 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.)
- Granted
Links
Landscapes
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a device for recognizing persons through an intelligent access control machine. The method comprises steps as follows: acquired person image information is imported into the intelligent access control machine to be used as a training sample, and the intelligent access control machine learns the training sample to train a verifier; the intelligent access control machine verifies IDs of access persons by the aid of the trained verifier and judges whether verification succeeds or not, if yes, the intelligent access control machine begins to acquire image information of access persons within a set range from the position where verification succeeds, extracts feature information, associates the IDs of the access persons, the feature information as well as the feature information generation time and position information and stores the information in a database; otherwise, the intelligent access control machine returns that verification fails; the verifier is retrained with associated data stored in the database used as the training sample, and returning is performed. The method and the device for recognizing the persons through the intelligent access control machine have the benefits as follows: the recognition rate is higher, the misrecognition rate is lower, and human body posture recognition accuracy is higher.
Description
Technical field
The present invention relates to identification field, particularly a kind of method and device being carried out personal identification by intelligent entrance guard machine.
Background technology
Along with the develop rapidly of Internet technology, mobile communication technology and artificial intelligence technology, people propose higher level safety and intelligent management demand to modern office and life area, common gate control system and access management system have not met the actual demand of modern, in order to comply with the development of intelligent building, intelligent residential district, gate control system must realize function that is more reliable, safer, intelligence more easily.
Personal identification ID identification at present based on face recognition technology is widely used in door access machine, but there is the problems such as discrimination is lower, false recognition rate is high.And be used in security protection camera based on the technology of human body attitude identification, when lacking prior imformation, often can only do simple identification, the accuracy of identification of human body attitude is lower.
Summary of the invention
The technical problem to be solved in the present invention is, the defect that above-mentioned discrimination for prior art is lower, false recognition rate is high, the accuracy of identification of human body attitude is lower, provides a kind of discrimination is higher, false recognition rate is lower, the accuracy of identification of human body attitude the is higher method and the device that are carried out personal identification by intelligent entrance guard machine.
The technical solution adopted for the present invention to solve the technical problems is: construct a kind of method of being carried out personal identification by intelligent entrance guard machine, and described intelligent entrance guard machine is provided with validator, and described method comprises the steps:
A) described intelligent entrance guard machine uses the personnel's image information gathered as training sample, trains described validator by learning described training sample;
B) described intelligent entrance guard machine uses the identity ID of validator to the personnel of discrepancy trained to verify, and judges whether to be proved to be successful, and in this way, performs step C); Otherwise, return authentication failed information;
C) from the position be proved to be successful, the image information of the discrepancy personnel be in setting range is gathered, characteristic information extraction; Described characteristic information comprises behavior characteristic information;
D) time of the identity ID of described discrepancy personnel, characteristic information, generation characteristic information is associated with positional information, and be stored in database;
E) using the data after the association be stored in described database as validator described in training sample re-training, return step B).
Undertaken in the method for personal identification by intelligent entrance guard machine of the present invention, described characteristic information also comprises face feature information.
Undertaken in the method for personal identification by intelligent entrance guard machine of the present invention, described steps A) comprise further:
A1) image information of collector, and it can be used as training sample to import in described intelligent entrance guard machine, described intelligent entrance guard machine extracts face feature information from described image information;
A2) described validator is trained according to described face feature information.
The invention still further relates to a kind of device realizing the method for carrying out personal identification above by intelligent entrance guard machine, described intelligent entrance guard machine is provided with validator, and described device comprises:
Gather training unit: for making described intelligent entrance guard machine use the personnel's image information gathered as training sample, train described validator by learning described training sample;
Checking judging unit: use for making described intelligent entrance guard machine the identity ID of validator to the personnel of discrepancy trained to verify, and judge whether to be proved to be successful, in this way, carry out image acquisition and feature extraction; Otherwise, return authentication failed information;
Image acquisition and feature extraction unit: for gathering the image information of the discrepancy personnel be in setting range from the position be proved to be successful, characteristic information extraction; Described characteristic information comprises behavior characteristic information;
Information association storage unit: for the time of the identity ID of described discrepancy personnel, characteristic information, the described characteristic information of generation is associated with positional information, and be stored in database;
Training sample re-training unit: for the data after the association that will be stored in described database as validator described in training sample re-training.
In device of the present invention, described characteristic information also comprises face feature information.
In device of the present invention, described collection training unit comprises further:
Facial feature extraction module: for the image information of collector, and it can be used as training sample to import in described intelligent entrance guard machine, described intelligent entrance guard machine extracts face feature information from described image information;
Training sample training module: for training described validator according to described face feature information.
Implement the method and the device that are carried out personal identification by intelligent entrance guard machine of the present invention, there is following beneficial effect: because intelligent entrance guard machine uses the personnel's image information gathered as training sample, identity ID checking is carried out by learning training sample training validator, and from the position be proved to be successful, gather the image information of the discrepancy personnel be in setting range, characteristic information extraction, the time of its identity ID, characteristic information, generation characteristic information is associated with positional information, and is stored in database; And it can be used as training sample re-training validator, so just can reach the object of the precision improving image recognition and behavioral value, so its discrimination is higher, false recognition rate is lower, the accuracy of identification of human body attitude is higher.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The process flow diagram of Fig. 1 to be the present invention by intelligent entrance guard machine undertaken method in the method for personal identification and device embodiment;
Fig. 2 is that in described embodiment, intelligent entrance guard machine uses the personnel's image information gathered as training sample, by the particular flow sheet of learning training sample training validator;
Fig. 3 is the structural representation of device in described embodiment.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under the prerequisite of not making creative work, all belongs to the scope of protection of the invention.
In the method for carrying out personal identification by intelligent entrance guard machine in the present invention and device embodiment, it carries out the process flow diagram of the method for personal identification as shown in Figure 1 by intelligent entrance guard machine.In the present embodiment, intelligent entrance guard machine is provided with validator (not shown).In Fig. 1, this method of carrying out personal identification by intelligent entrance guard machine comprises the steps:
Step S01 intelligent entrance guard machine uses the personnel's image information training sample gathered, by learning training sample training validator: in this step, to authorizing personnel's link (authorize come in and go out authority), the image information of artificial collector, intelligent entrance guard machine uses the personnel's image information training sample gathered, by learning training sample training validator.
Step S02 intelligent entrance guard machine uses the identity ID of validator to the personnel of discrepancy trained to verify, and judge whether to be proved to be successful: in this step, intelligent entrance guard machine in the course of the work, the identity ID of validator to the personnel of discrepancy trained is used to verify, and judge whether to be proved to be successful, if the result judged is yes, then perform S04; Otherwise, perform step S03.
Step S03 returns authentication failed information: if the judged result of above-mentioned steps S02 is no, then perform this step.In this step, return authentication failed information.
Step S04 gathers the image information of the discrepancy personnel be in setting range from the position be proved to be successful, characteristic information extraction: in this step, from the position be proved to be successful, collection is in the image information of the discrepancy personnel of (in specialized range) in setting range, characteristic information extraction, this characteristic information comprises behavior characteristic information.By the behavior characteristic information (posture feature information) extracted in conjunction with identity ID, the posture feature of discrepancy personnel individuality can be obtained, form a large amount of prior imformations, improve the discrimination of human body abnormal behaviour.
Certainly, in order to improve discrimination further, reduce false recognition rate, the accuracy of identification of further raising human body attitude, when characteristic information extraction, the characteristic information extracted also comprises face feature information, namely when characteristic information extraction, extract behavior characteristic information and face feature information simultaneously.Like this, by discrimination being improved in conjunction with the face feature information of human body and behavior characteristic information, the identity id information of personnel is confirmed more accurately.
The time of the identity ID of the personnel of discrepancy, characteristic information, generation characteristic information associates with positional information by step S05, and be stored in database: in this step, the time of the identity ID of the personnel of discrepancy, characteristic information, generation behavior characteristic information is associated with positional information, and is stored in database.Certainly, also can by the face feature information of the personnel of discrepancy stored in database.
Step S06 using the data after the association be stored in database as training sample re-training validator: in this step, using the data after the association be stored in database as training sample re-training validator, execute this step, return step S02.Using confirmed data as new sample training validator, intelligent entrance guard machine is just provided with self-learning function; Intelligent entrance guard machine, by the study to new confirmed data, can improve the precision of personal identification and the identification of personnel's abnormal operation.And common door access machine without self-learning function can only identify according to the face information of typing, will reduce discrimination (such as light change, hair style change, local trauma, age increase) when face information changes, and the intelligent entrance guard machine in the present embodiment can improve discrimination by learning.By identifying in conjunction with personnel identity ID, the method for human behavior identification and the self study of intelligent entrance guard machine, the new data produced are learnt, make intelligent entrance guard facility have higher precision.
For the present embodiment, above-mentioned steps S01 also can refinement further, and the process flow diagram after its refinement as shown in Figure 2.In Fig. 2, above-mentioned steps S01 comprises further:
The image information of step S11 collector, and it can be used as training sample to import in intelligent entrance guard machine, intelligent entrance guard machine extracts face feature information from image information: in this step, the image information of artificial collector, and the image information of the personnel gathered is imported in intelligent entrance guard machine as training sample, intelligent entrance guard machine extracts face feature information from the image information of the personnel gathered.
Step S12 trains validator according to face feature information: in this step, according to face feature information training validator.
The present embodiment also relates to a kind of device realizing the method for carrying out personal identification above by intelligent entrance guard machine, and its structural representation as shown in Figure 3.In the present embodiment, intelligent entrance guard machine is provided with validator (not shown).In Fig. 3, this device comprises collection training unit 1, checking judging unit 2, image acquisition and feature extraction unit 3, information association storage unit 4 and training sample re-training unit 5; Wherein, gathering training unit 1 uses the personnel's image information gathered as training sample, by learning training sample training validator for making intelligent entrance guard machine; Checking judging unit 2 is verified for the identity ID of validator to discrepancy personnel making intelligent entrance guard machine use to have trained, and judges whether to be proved to be successful, and in this way, carries out image acquisition and feature extraction; Otherwise, return authentication failed information; Image acquisition and feature extraction unit 3 for gathering the image information of the discrepancy personnel be in setting range, characteristic information extraction from the position be proved to be successful; Above-mentioned characteristic information comprises behavior characteristic information; Certainly, certainly, in order to improve discrimination further, reduce false recognition rate, improve the accuracy of identification of human body attitude further, when characteristic information extraction, the characteristic information extracted also comprises face feature information.
Information association storage unit 4 for being associated with positional information the time of the identity ID of the personnel of discrepancy, behavior characteristic information, generation characteristic information, and is stored in database; Training sample re-training unit 5 for the data after the association that will be stored in database as training sample re-training validator.So just can reach the object of the precision improving image recognition and behavioral value, so its discrimination is higher, false recognition rate is lower, the accuracy of identification of human body attitude is higher.
In the present embodiment, gather training unit 1 and comprise facial feature extraction module 11 and training sample training module 12 further; Wherein, facial feature extraction module 11 for the image information of collector, and it can be used as training sample to import in intelligent entrance guard machine, and intelligent entrance guard machine extracts face feature information from image information; Training sample training module 12 is for training validator according to face feature information.
In a word, in the present embodiment, by extracting face feature information from the image information (sample of typing) gathered, according to these characteristic informations training validator, identity ID checking is carried out.Intelligent entrance guard machine gathers the image information of the personnel be in setting range from the position be proved to be successful, characteristic information extraction (comprising behavior characteristic information and face feature information), the characteristic information extracted was associated with time and position, and be stored in database, confirmed data can be used as new sample training validator, to reach the object of the precision improving image recognition and behavioral value.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (6)
1. carried out a method for personal identification by intelligent entrance guard machine, it is characterized in that, described intelligent entrance guard machine is provided with validator, and described method comprises the steps:
A) described intelligent entrance guard machine uses the personnel's image information gathered as training sample, trains described validator by learning described training sample;
B) described intelligent entrance guard machine uses the identity ID of validator to the personnel of discrepancy trained to verify, and judges whether to be proved to be successful, and in this way, performs step C); Otherwise, return authentication failed information;
C) from the position be proved to be successful, the image information of the discrepancy personnel be in setting range is gathered, characteristic information extraction; Described characteristic information comprises behavior characteristic information;
D) time of the identity ID of described discrepancy personnel, characteristic information, generation characteristic information is associated with positional information, and be stored in database;
E) using the data after the association be stored in described database as validator described in training sample re-training, return step B).
2. method of being carried out personal identification by intelligent entrance guard machine according to claim 1, be is characterized in that, described characteristic information also comprises face feature information.
3. method of being carried out personal identification by intelligent entrance guard machine according to claim 1 and 2, be is characterized in that, described steps A) comprise further:
A1) image information of collector, and it can be used as training sample to import in described intelligent entrance guard machine, described intelligent entrance guard machine extracts face feature information from described image information;
A2) described validator is trained according to described face feature information.
4. realize the device being carried out the method for personal identification by intelligent entrance guard machine as claimed in claim 1, it is characterized in that, described intelligent entrance guard machine is provided with validator, and described device comprises:
Gather training unit: for making described intelligent entrance guard machine use the personnel's image information gathered as training sample, train described validator by learning described training sample;
Checking judging unit: use for making described intelligent entrance guard machine the identity ID of validator to the personnel of discrepancy trained to verify, and judge whether to be proved to be successful, in this way, carry out image acquisition and feature extraction; Otherwise, return authentication failed information;
Image acquisition and feature extraction unit: for gathering the image information of the discrepancy personnel be in setting range from the position be proved to be successful, characteristic information extraction; Described characteristic information comprises behavior characteristic information;
Information association storage unit: for the time of the identity ID of described discrepancy personnel, characteristic information, generation characteristic information is associated with positional information, and be stored in database;
Training sample re-training unit: for the data after the association that will be stored in described database as validator described in training sample re-training.
5. device according to claim 4, is characterized in that, described characteristic information also comprises face feature information.
6. the device according to claim 4 or 5, is characterized in that, described collection training unit comprises further:
Facial feature extraction module: for the image information of collector, and it can be used as training sample to import in described intelligent entrance guard machine, described intelligent entrance guard machine extracts face feature information from described image information;
Training sample training module: for training described validator according to described face feature information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510644835.5A CN105184932B (en) | 2015-10-08 | 2015-10-08 | A kind of method and device that personal identification is carried out by intelligent entrance guard machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510644835.5A CN105184932B (en) | 2015-10-08 | 2015-10-08 | A kind of method and device that personal identification is carried out by intelligent entrance guard machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105184932A true CN105184932A (en) | 2015-12-23 |
CN105184932B CN105184932B (en) | 2017-12-22 |
Family
ID=54906980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510644835.5A Active CN105184932B (en) | 2015-10-08 | 2015-10-08 | A kind of method and device that personal identification is carried out by intelligent entrance guard machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105184932B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025436A (en) * | 2017-03-13 | 2017-08-08 | 西安电子科技大学 | A kind of self refresh human intrusion detection method based on confidence level |
CN107395421A (en) * | 2017-07-27 | 2017-11-24 | 浙江宇视科技有限公司 | Acquisition method and system |
CN107590888A (en) * | 2017-09-09 | 2018-01-16 | 安徽省未来博学信息技术有限公司 | A kind of building are registered one's residence gate control system |
CN108765660A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | Security system authorization method is obtained based on associated AP P |
CN108765662A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | Security system authorization method is obtained based on intelligence learning |
CN110895838A (en) * | 2018-09-12 | 2020-03-20 | 格力电器(武汉)有限公司 | Intelligent door lock control method and device and intelligent door lock |
CN112184962A (en) * | 2020-09-29 | 2021-01-05 | 中国银行股份有限公司 | Control method, system and control device for digital lock of cash box |
CN113553888A (en) * | 2020-04-26 | 2021-10-26 | 浙江宇视科技有限公司 | Personnel identity verification method, device, equipment and storage medium |
CN115497146A (en) * | 2022-10-18 | 2022-12-20 | 支付宝(杭州)信息技术有限公司 | Model training method and device and identity verification method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11175718A (en) * | 1997-12-12 | 1999-07-02 | Toshiba Corp | Person recognizing device and its method |
CN1494037A (en) * | 2002-11-01 | 2004-05-05 | ��ʽ���綫֥ | Apparatus and method for identifying personnel and passage controller |
CN201838050U (en) * | 2010-08-19 | 2011-05-18 | 秦和平 | Intelligent anti-terrorist security inspection door device |
CN202758408U (en) * | 2012-08-16 | 2013-02-27 | 山西铭慧科技有限公司 | Management system for mine personnel |
CN103985172A (en) * | 2014-05-14 | 2014-08-13 | 南京国安光电科技有限公司 | An access control system based on three-dimensional face identification |
-
2015
- 2015-10-08 CN CN201510644835.5A patent/CN105184932B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11175718A (en) * | 1997-12-12 | 1999-07-02 | Toshiba Corp | Person recognizing device and its method |
CN1494037A (en) * | 2002-11-01 | 2004-05-05 | ��ʽ���綫֥ | Apparatus and method for identifying personnel and passage controller |
CN201838050U (en) * | 2010-08-19 | 2011-05-18 | 秦和平 | Intelligent anti-terrorist security inspection door device |
CN202758408U (en) * | 2012-08-16 | 2013-02-27 | 山西铭慧科技有限公司 | Management system for mine personnel |
CN103985172A (en) * | 2014-05-14 | 2014-08-13 | 南京国安光电科技有限公司 | An access control system based on three-dimensional face identification |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025436A (en) * | 2017-03-13 | 2017-08-08 | 西安电子科技大学 | A kind of self refresh human intrusion detection method based on confidence level |
CN107395421A (en) * | 2017-07-27 | 2017-11-24 | 浙江宇视科技有限公司 | Acquisition method and system |
CN107590888A (en) * | 2017-09-09 | 2018-01-16 | 安徽省未来博学信息技术有限公司 | A kind of building are registered one's residence gate control system |
CN108765660A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | Security system authorization method is obtained based on associated AP P |
CN108765662A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | Security system authorization method is obtained based on intelligence learning |
CN110895838A (en) * | 2018-09-12 | 2020-03-20 | 格力电器(武汉)有限公司 | Intelligent door lock control method and device and intelligent door lock |
CN113553888A (en) * | 2020-04-26 | 2021-10-26 | 浙江宇视科技有限公司 | Personnel identity verification method, device, equipment and storage medium |
CN113553888B (en) * | 2020-04-26 | 2024-03-08 | 浙江宇视科技有限公司 | Personnel identity verification method, device, equipment and storage medium |
CN112184962A (en) * | 2020-09-29 | 2021-01-05 | 中国银行股份有限公司 | Control method, system and control device for digital lock of cash box |
CN115497146A (en) * | 2022-10-18 | 2022-12-20 | 支付宝(杭州)信息技术有限公司 | Model training method and device and identity verification method and device |
Also Published As
Publication number | Publication date |
---|---|
CN105184932B (en) | 2017-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105184932A (en) | Method and device for recognizing persons through intelligent access control machine | |
CN111460962B (en) | Face recognition method and face recognition system for mask | |
CN102542258B (en) | Imaging device based on finger biometric information and multimoding identity recognition method | |
CN104851140A (en) | Face recognition-based attendance access control system | |
CN101661557B (en) | Face recognition system and face recognition method based on intelligent card | |
CN107944838A (en) | A kind of intelligent barrier gate Field Monitoring System and method | |
CN101872413A (en) | Fingerprint and face integrated identity authentication system | |
CN105631272A (en) | Multi-safeguard identity authentication method | |
CN107045744A (en) | A kind of intelligent villa entrance guard authentication method and system | |
CN106203294A (en) | The testimony of a witness unification auth method analyzed based on face character | |
CN106919921B (en) | Gait recognition method and system combining subspace learning and tensor neural network | |
CN202130312U (en) | Driver fatigue driving monitoring device | |
CN103593598A (en) | User online authentication method and system based on living body detection and face recognition | |
CN201845343U (en) | Image acquisition device for human face recognition | |
CN101697514A (en) | Method and system for identity authentication | |
CN110287813A (en) | Personal identification method and system | |
CN108376215A (en) | A kind of identity identifying method | |
CN111862413A (en) | Method and system for realizing epidemic situation resistant non-contact multidimensional identity rapid identification | |
CN110555926A (en) | Access control method based on multi-certificate recognition and corresponding device | |
CN109635625A (en) | Smart identity checking method, equipment, storage medium and device | |
CN114333011B (en) | Network training method, face recognition method, electronic device and storage medium | |
CN111723595A (en) | Personnel identity identification method and system | |
CN110908718A (en) | Face recognition activated voice navigation method, system, storage medium and equipment | |
CN115147887A (en) | Face recognition rate improving method, access control device and computer-readable storage medium | |
CN109272616A (en) | A kind of entrance guard controlling method and system based on recognition of face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |