CN109977645A - A kind of identification system - Google Patents
A kind of identification system Download PDFInfo
- Publication number
- CN109977645A CN109977645A CN201910205499.2A CN201910205499A CN109977645A CN 109977645 A CN109977645 A CN 109977645A CN 201910205499 A CN201910205499 A CN 201910205499A CN 109977645 A CN109977645 A CN 109977645A
- Authority
- CN
- China
- Prior art keywords
- module
- identification
- image
- terminal device
- identification system
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of identification systems, comprising: terminal device and back-end controller;The terminal device and the back-end controller pass through network connection communication;The terminal device includes image capture module, In vivo detection module, range finder module and image pre-processing module 1;The back-end controller includes training module, identification module and memory module;Further include: characteristic extracting module and image pre-processing module 2, the characteristic extracting module and image pre-processing module 2 are set on terminal device or back-end controller;System is, it can be achieved that efficient identification user identity through the invention, it is ensured that accuracy, the authenticity of user identity, help realize that efficient rapid authentication is current, and without combining identity document etc., other assist in identifying judgement, bring convenience to user;Present system design architecture is flexible, efficiency of service is high, can meet the identification demand of different user amount and heterogeneous networks and computing resource.
Description
Technical field
The present invention relates to technical field of biometric identification, and in particular to a kind of identification system.
Background technique
In recent years, with the arrival of the high speed development of information technology and big data era, biological identification technology applies city
Field rapid growth, it is especially more prominent and typical with the landing application of face recognition technology.Since 2016, recognition of face is in silver
The scenes such as row, security, finance, traffic, education, e-commerce apply frequent brush screen, have started New Generation of Intelligent identification
Upsurge, the convenient experience and help for having brought wisdom life improve work efficiency.
But the accuracy of current recognition of face is easy to be influenced by various, on the one hand, due to the growth microvariations of face
And expression is changeable, so that the visual pattern of face can have very big difference, thus produces bigger effect to the accuracy of identification;Separately
On the one hand, recognition of face is easy by external environments such as light and blocks equal disturbed conditions and influenced, the acquisition pair of character image
Around light environment it is sensitive, light difference largely will affect the accuracy of identification, and the hair of human body face, beard
The influence of the equal disturbing factors such as shelters and makeup also can have larger impact to the accuracy rate of identification.Furthermore recognition of face
It is also easy to be occurred claiming the identity of others fraudulently by spoofing attacks such as photo, videos to carry out the loophole of illegal traffic.Due to above-mentioned factor
It influences, in practical applications, the result of face identification system identification usually also needs to operate with identity document or code entry etc.
Carry out user identification confirmation is combined, to overcome misrecognition or photo etc. to cheat, so that it is guaranteed that the accuracy of user identity and true
Reality.
Recognition of face is in actually landing application, other than having higher requirement to recognition accuracy, while also requiring high
Effect, especially AT STATION, airport, parking lot, large-scale exhibitions, some easily intensive places of fluid capacitance such as tourist attractions, speed one
Denier, which slows down, will be greatly reduced the practicability of recognition of face.The speed of recognition of face is easy to be influenced by various, including identification
The factors such as angle, identification background, photo resolution, illumination.
Summary of the invention
The technical problem to be solved by the present invention is to aiming at the above shortcomings existing in the prior art, provide a kind of identity knowledge
Other system, to realize efficient identification user identity, it is ensured that accuracy, the authenticity of user identity, help are realized efficiently quickly logical
Row, without combining identity document etc., other assist in identifying judgement, bring convenience to user.
To realize the above goal of the invention, the technical solution adopted is that:
A kind of identification system, comprising: terminal device and back-end controller;The terminal device and the back-end controller are logical
Cross network connection communication;
The terminal device includes image capture module, In vivo detection module, range finder module and image pre-processing module 1, described
Image capture module is responsible for acquiring user's character image, and the In vivo detection module is used to carry out In vivo detection to user, described
Range finder module is used to detect the distance of target person, and described image preprocessing module 1 is for carrying out image basis pretreatment;
The back-end controller includes training module, identification module and memory module, and the training module is known for user identity
Not Xun Lian, the identification module be used for user identity identification, the memory module be used for storing user's registered information and characteristic
According to;
Further include: characteristic extracting module and image pre-processing module 2, the characteristic extracting module is for extracting character features, institute
Image pre-processing module 2 is stated to pre-process for image recognition;The characteristic extracting module and image pre-processing module 2 are set to end
In end equipment or back-end controller.
Further, further includes: site controller, the site controller include the characteristic extracting module and the figure
As preprocessing module 2, and pass through network and the terminal device and the back-end controller connecting communication.
Further, the site controller further includes the identification module and weight library synchronization module, the weight library
Synchronization module is used to synchronize the model of the training module output.
Further, the terminal device and the site controller are several, and the site controller uses physics
Distributed computing.
Further, the back-end controller is arranged using the service grid environment based on Kubernetes.
Further, the site controller and the terminal device are communicated by LAN connection.
Further, the site controller further includes advertisement control module, and the advertisement control module is wide for controlling
It accuses and plays.
Further, further includes: advertising management platform, the advertising management platform and the site controller pass through network
Connecting communication, the advertising management platform are used for releasing advertisements content.
Further, the character image is whole body character image;The character features include: human body attitude feature and face
Portion's posture feature.
Further, described image basis pretreatment includes but is not limited to: dimension of picture adjustment, brightness adjustment and gamma are rectified
Just;Described image identification pretreatment includes but is not limited to: target positioning, the most previous people of extraction and personage confine.
Identification system of the invention, has the advantages that
(1) using identification system of the invention, it can be achieved that efficient identification user identity, it is ensured that the accuracy of user identity,
Authenticity, help realize that efficient rapid authentication is current, and without combining identity document etc., other assist in identifying judgement, bring to user
It is convenient.
(2) identification system design architecture of the invention is flexible, efficiency of service is high, can meet different user amount and not
With the identification demand of network and computing resource, resource utilization and recognition efficiency can be effectively improved, and in network failure
Shi Yiran can carry out identity identifying and authenticating, so as to preferably guarantee smooth passage.
Detailed description of the invention
Fig. 1 is the identification system structure chart of the embodiment of the present invention one.
Fig. 2 is the identification system structure chart of the embodiment of the present invention two.
Fig. 3 is the identification system structure chart of the embodiment of the present invention three.
Fig. 4 is identification system longitudinal extension configuration diagram of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The purpose of the present invention is to provide a kind of identification systems, to realize efficient identification user identity, it is ensured that user
Efficient fast passing is realized in accuracy, the authenticity of identity, help, and without combining identity document etc., other assist in identifying judgement,
It is brought convenience to user.The principle and embodiment of identification system of the invention described in detail below, makes this field skill
Art personnel do not need creative work and are appreciated that technology contents of the invention.
Embodiment one
As shown in Figure 1, a kind of identification system of the present invention includes: terminal device and back-end controller, terminal device and rear end
Controller passes through network connection communication.
Terminal device includes that image capture module, In vivo detection module, range finder module, image pre-processing module 1, image are pre-
Processing module 2 and characteristic extracting module, image capture module are responsible for acquiring the character image of user, it is preferred that are taken the photograph using binocular
As head acquisition character image, character image is whole body character image, and passing through acquisition whole body character image can get more fully people
Object characteristic information, to obtain higher recognition accuracy;In vivo detection module is used to carry out In vivo detection to user, with effective
Prevent photo, video etc. from cheating, it is preferred that combine carry out In vivo detection using optical flow method and infrared stripes shadow casting technique;It surveys
It is used to detect the distance of target person away from module, when detecting target person in specified identification region, system is to target person
Object image is acquired, it is preferred that using it is infrared, feel or ultrasonic method carry out ranging;Image pre-processing module 1 is for carrying out
Image basis pretreatment, image basis pretreatment include dimension of picture adjustment, brightness adjustment and Gamma correction etc., pass through image base
Plinth is pre-processed to obtain higher picture quality;Image pre-processing module 2 is pre-processed for image recognition, image recognition pretreatment
It confines including target positioning, the most previous people of extraction and personage, is pre-processed by image recognition preferably to obtain identification target;
Characteristic extracting module is for extracting character features, it is preferred that and character features include: human body attitude feature and facial pose feature,
Identification decision is carried out by the combination of human body attitude feature and facial pose feature, not only recognition accuracy is higher, to single spy
The identification of sign requires reduction, it is not easy to be influenced by light, environment, makeup etc., recognition efficiency is higher, it is preferred that uses multichannel
Convolutional neural networks extract character features.
Back-end controller includes training module, identification module and memory module, and training module is instructed for user identity identification
Practice, obtain identification model, it is preferred that identification training is carried out using multichannel convolutive neural network;Identification module is used
Family identification, and export recognition result;Memory module is used for storing user's registered information and characteristic, and each user is every
Characteristic when secondary identification is stored, and recognition training sample is accumulated, to continue to optimize identification model, it is accurate to improve identification
Degree and recognition efficiency.
The present embodiment identification system can be applied to cell gate inhibition, office attendance and various setting gates and carry out identity
The place that could be passed through after verifying, such as large-scale exhibitions, great meeting enter and leave monitoring scene etc..
The method process for carrying out identification using the present embodiment identification system is as follows:
User first passes through APP in advance and registers, and registration process includes typing user information, such as cell-phone number or identification card number, leads to
Fixed register machine acquisition user's registration whole body images are crossed, registration can be completed.User's registration information will be stored in back-end controller.
After succeeding in registration, user is the place that can be used identification system of the present invention that disengaging is facilitated to need authentication, without any
Operation assists verifying certificate without other.
When user's entry/exit, durings walking close to gate/gate inhibition etc., firstly, the range finder module of terminal device detects mesh
After the distance of mark user meets identification required distance, In vivo detection module starts to carry out In vivo detection to target, and In vivo detection is complete
At and after meeting, image capture module starts to carry out whole body images acquisition to target;After Image Acquisition, image pre-processing module 1
The pretreatment of the basis such as dimension of picture adjustment, brightness adjustment and Gamma correction is carried out to image;After the completion of the pretreatment of basis, image is pre-
Processing module 2 carries out identification pretreatment to image, including target positioning, the most previous people of extraction and personage confine;Image recognition
After the completion of pretreatment, characteristic extracting module extracts character features, comprising: human body attitude feature and facial pose feature, Ren Wute
After the completion of sign is extracted, then character features data are sent to by back-end controller by network and are identified;The knowledge of back-end controller
Other module identifies user by characteristic, and stores characteristic, after identifying successfully, Xiang Men by memory module
Taboo/gate system transmission user identity meets as a result, gate inhibition/gate system is received in compliance with information and opens the door/and opens a sluice gate, user
It is current.Entire identification process is fast rapid, and user completes above-mentioned identity identifying and authenticating and reality during walking naturally
It now opens the door/opens a sluice gate, identification process user, without carrying out any operation, greatly facilitates user and go out without deliberately cooperating and stopping
Enter to pass through and improve traffic efficiency.
Current embodiment require that terminal device has sufficient computing resource, located in advance by carrying out image recognition in terminal device
Reason and character features extract operation, can greatly reduce and be transferred to the data volume of back-end controller, thus the requirement to network bandwidth
It is lower.
Embodiment two
Fig. 2 is the identification system structure chart of another embodiment of the present invention.It is with one difference of embodiment, the present embodiment feature
Extraction module and image pre-processing module 2 are set on back-end controller, and image recognition pretreatment and character features extract operation
It is completed by back-end controller, thus the computing resource of terminal device is required to reduce, but the requirement to network bandwidth is relatively high.
It is using the method process that the present embodiment identification system carries out identification with one difference of embodiment, terminal
After equipment completes image basis pretreatment, the pretreated image in basis is sent to back-end controller, by back-end controller into
The pretreatment of row image recognition and character features extract operation, and subsequent identification step is the same as example 1.
The present embodiment identification system can be applied to cell gate inhibition, office attendance and various setting gates and carry out identity
The place that could be passed through after verifying, such as large-scale exhibitions, great meeting enter and leave monitoring scene etc..
Embodiment three
Fig. 3 is the identification system structure chart of yet another embodiment of the invention.In the present embodiment, identification system of the present invention
Applied to Metro Passenger identification lockage.As shown in figure 3, the subway based on identification system of the present invention crosses brake system packet
It includes: terminal device, site controller, back-end controller, advertising management platform, ticket management platform and gate equipment, wherein lock
Machine equipment is divided into enter the station gate equipment and outbound gate equipment.Specifically, terminal device be respectively arranged in enter the station gate equipment and
In outbound gate equipment, terminal device and gate equipment are controlled by serial ports connecting communication, site controller and terminal device, rear end
Device processed passes through network connection communication, advertisement pipe by network connection communication, ticket management platform and back-end controller, gate equipment
Platform and site controller pass through network connection communication.Preferably, terminal device and site controller are LAN connection, from
And guarantee sufficient bandwidth resources, the transmission of personage's whole body images data can be better meet.
Terminal device includes that image capture module, In vivo detection module, range finder module, image pre-processing module 1, image are pre-
Processing module 2 and characteristic extracting module, image capture module are responsible for acquiring character image when user's lockage, it is preferred that personage
Image is whole body character image, can get more fully person characteristic information by acquisition whole body character image, thus obtain compared with
High recognition accuracy;In vivo detection module is used to carry out In vivo detection to lockage user, to effectively prevent photo, video etc. to take advantage of
Swindleness;Range finder module is used to detect the distance of target person, and when detecting target person in specified identification region, system is to mesh
Mark character image is acquired;Image pre-processing module 1 includes figure for carrying out image basis pretreatment, image basis pretreatment
Chip size adjustment, brightness adjustment and Gamma correction etc., are pre-processed by image basis to obtain higher picture quality;Image is pre-
Processing module 2 is pre-processed for image recognition, and image recognition pretreatment includes that target positioning, the most previous people of extraction and personage confine
Deng being pre-processed by image recognition preferably to obtain identification target;Characteristic extracting module is for extracting character features, preferably
, character features include: human body attitude feature and facial pose feature, pass through the knot of human body attitude feature and facial pose feature
Close and carry out identification decision, not only recognition accuracy is higher, requires reduction to the identification of single feature, it is not easy to by light, environment,
Makeup etc. influences.
Back-end controller includes training module, identification module and memory module, and training module is instructed for user identity identification
Practice, obtains identification model;Identification module is used for lockage user identity identification, and exports recognition result;Memory module is for storing
User's registration information and characteristic, characteristic when lockage that each user is each store, and accumulate recognition training sample
This improves identification precision and recognition efficiency to continue to optimize identification model.
Site controller includes characteristic extracting module, image pre-processing module 2, advertisement control module, identification module and power
Weight library synchronization module, wherein weight library synchronization module is used to synchronize the model of back-end controller training module output, to facilitate and
Weight database needed for Shi Gengxin identification;The feature extraction of characteristic extracting module and image pre-processing module 2 and terminal device
Module and image pre-processing module 2 are identical, are respectively used to extract character features and pre-process for image recognition;Identification module with
The identification module of back-end controller is identical, is used for lockage user identity identification, and export recognition result;Advertisement control module is used for
It controls advertisement to play, the ad content of docking advertising management platform publication.Advertising management platform is mainly responsible for update and publication is wide
Accuse content.
Ticket management platform includes bill unit, payment unit and storage unit, and bill unit is responsible for providing bill, payment
Unit is that user completes reimbursement of expense, and memory module is recorded for store transaction;
Gate equipment is for receiving bill and regulating gate opening and closing.Preferably, gate equipment is equipped with BLE module, for receiving
Billing information.
Specifically, terminal device and site controller are several.Terminal device and site controller are mounted on eachly
Iron website, site controller are calculated using physical distribution formula.Back-end controller uses the service grid environment based on Kubernetes
(Service mesh) is arranged.
It is as follows that subway lockage method process is carried out using the present embodiment identification system:
User first passes through APP in advance and registers, and registration process includes typing user information, such as cell-phone number, identification card number, passes through
Fixed register machine acquires user's registration whole body images, and to account charging or opens and exempt from close payment, and user's registration information will store
In back-end controller and ticket management platform.After succeeding in registration, user identification system of the present invention can be used to carry out lockage
By bus.
When user entry/exit station, during walking close to gate: firstly, the range finder module of terminal device detects that target is used
After the distance at family meets identification required distance, In vivo detection module starts to carry out target In vivo detection, and In vivo detection is completed simultaneously
After meeting, image capture module starts to carry out whole body images acquisition to target;After Image Acquisition, 1 pair of image pre-processing module figure
As carrying out the pretreatment of the basis such as dimension of picture adjustment, brightness adjustment and Gamma correction.Secondly, passing through after the completion of the pretreatment of basis
Image pre-processing module 2 carries out identification pretreatment to image, including target positioning, the most previous people of extraction and personage confine;Figure
After the completion of identification pretreatment, character features are extracted by characteristic extracting module, comprising: human body attitude feature and facial pose are special
Sign, above-mentioned image recognition pretreatment and character features extraction step can be completed in terminal device or be completed on site controller.
After the completion of character features extract, then by identification module user is identified, and export recognition result, which can be
It is completed on site controller or on back-end controller.After identifying successfully, from back-end controller to ticket management platform request bill;
Bill is sent to lock by network after back-end controller receives bill to ticket management platform by side controller transmission bill backward
The BLE module of machine equipment, BLE module inform that gate is opened a sluice gate after receiving bill, and user can lockage.User completes outbound
Afterwards, customer transaction data are sent to ticketing service equipment by network and are managed and store by outbound gate equipment.
The present embodiment, can be by site controller by the way that identification module and weight library synchronization module is arranged in site controller
Identification step is completed, since terminal device and site controller are LAN connection, in back-end controller network failure
It still ensures that normal identification certification, offline bill can be obtained by gate terminal after identifying successfully, so that it is guaranteed that Metro Passenger
Smooth passage.
Fig. 4 is identification system longitudinal extension configuration diagram of the present invention.As shown in figure 4, Image Acquisition, In vivo detection
It need to be realized on the terminal device with object ranging function, and image recognition pretreatment and character features abstraction function can be set in terminal
Flexible telescopic arrangement is realized on standby, site controller and/or back-end controller;Identity recognition function then can be in site controller
And/or flexible telescopic arrangement is realized on back-end controller.The character features of terminal device extract and image recognition preprocessing function
It is extracted with the character features of site controller and image recognition preprocessing function constitutes level-one and stretches;The image of site controller is known
Not Yu Chuli, character features extract and extract with the pretreatment of the image recognition of identity recognition function and back-end controller, character features
It is flexible that second level is constituted with identity recognition function.It therefore, can be according to user volume, network and meter using identification system of the present invention
Calculate the characteristics of demand of resource, the above-mentioned related Telescopic module of flexible setting, with meet different user amount and heterogeneous networks and
The identification demand of computing resource improves recognition efficiency.
In summary, using identification system of the invention, it can be achieved that efficient identification user identity, it is ensured that user identity
Accuracy, authenticity, help realizes that efficient rapid authentication is current, and without combining identity document etc., other assist in identifying judgement,
It is brought convenience to user.
Identification system design architecture of the invention is flexible flexibly, efficiency of service is high, can meet the knowledge of different user amount
Other demand can effectively improve resource utilization and recognition efficiency, and identity knowledge can be still carried out in network failure
It does not authenticate, so as to preferably guarantee smooth passage.
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary implementation that uses
Mode, however the present invention is not limited thereto.All within the spirits and principles of the present invention, it is made it is any modification, equally replace
It changes and improves, should be included within the scope of the present invention.
Claims (10)
1. a kind of identification system characterized by comprising terminal device and back-end controller;The terminal device and institute
It states back-end controller and passes through network connection communication;
The terminal device includes image capture module, In vivo detection module, range finder module and image pre-processing module 1, described
Image capture module is responsible for acquiring user's character image, and the In vivo detection module is used to carry out In vivo detection to user, described
Range finder module is used to detect the distance of target person, and described image preprocessing module 1 is for carrying out image basis pretreatment;
The back-end controller includes training module, identification module and memory module, and the training module is known for user identity
Not Xun Lian, the identification module be used for user identity identification, the memory module be used for storing user's registered information and characteristic
According to;
Further include: characteristic extracting module and image pre-processing module 2, the characteristic extracting module is for extracting character features, institute
Image pre-processing module 2 is stated to pre-process for image recognition;The characteristic extracting module and image pre-processing module 2 are set to end
In end equipment or back-end controller.
2. identification system according to claim 1, which is characterized in that further include: site controller, the website control
Device processed includes the characteristic extracting module and described image preprocessing module 2, and by network and the terminal device with it is described
Back-end controller connecting communication.
3. identification system according to claim 2, which is characterized in that the site controller further includes the identification
Module and weight library synchronization module, weight library synchronization module are used to synchronize the model of the training module output.
4. identification system according to claim 2 or 3, which is characterized in that the terminal device and the website control
Device processed is several, and the site controller is calculated using physical distribution formula.
5. identification system according to claim 1, which is characterized in that the back-end controller is used and is based on
The service grid environment of Kubernetes is arranged.
6. identification system according to claim 2, which is characterized in that the site controller and the terminal device
It is communicated by LAN connection.
7. identification system according to claim 2, which is characterized in that the site controller further includes advertisement control
Module, the advertisement control module is for controlling advertisement broadcasting.
8. identification system according to claim 7, which is characterized in that further include: advertising management platform, the advertisement
Platform and the site controller are managed by network connection communication, the advertising management platform is used for releasing advertisements content.
9. identification system according to claim 1, which is characterized in that the character image is whole body character image;
The character features include: human body attitude feature and facial pose feature.
10. identification system according to claim 1, which is characterized in that the pretreatment of described image basis includes: picture
Size adjusting, brightness adjustment and Gamma correction;Described image identification pretreatment includes: target positioning, extracts most previous people and people
Object is confined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205499.2A CN109977645A (en) | 2019-03-18 | 2019-03-18 | A kind of identification system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205499.2A CN109977645A (en) | 2019-03-18 | 2019-03-18 | A kind of identification system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109977645A true CN109977645A (en) | 2019-07-05 |
Family
ID=67079387
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910205499.2A Pending CN109977645A (en) | 2019-03-18 | 2019-03-18 | A kind of identification system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109977645A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111031125A (en) * | 2019-12-10 | 2020-04-17 | 咪付(广西)网络技术有限公司 | User data pushing method and system based on travel record |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102811222A (en) * | 2012-08-09 | 2012-12-05 | 浪潮电子信息产业股份有限公司 | Identity identification security method based on cloud computing |
CN105335750A (en) * | 2014-06-11 | 2016-02-17 | 数伦计算机技术(上海)有限公司 | Client identity identification system and identification method |
WO2016112630A1 (en) * | 2015-01-12 | 2016-07-21 | 芋头科技(杭州)有限公司 | Image recognition system and method |
CN107247941A (en) * | 2017-06-22 | 2017-10-13 | 易容智能科技(苏州)有限公司 | The sampling of accurate face and recognition methods of a kind of high hardware resiliency |
WO2017181769A1 (en) * | 2016-04-21 | 2017-10-26 | 腾讯科技(深圳)有限公司 | Facial recognition method, apparatus and system, device, and storage medium |
CN107978051A (en) * | 2017-12-15 | 2018-05-01 | 亿城通智能科技(大冶)有限公司 | A kind of access control system and method based on recognition of face |
CN207909166U (en) * | 2018-03-09 | 2018-09-25 | 广东万峯信息科技有限公司 | Public transport based on face recognition technology is pursued and captured an escaped prisoner system |
CN109215139A (en) * | 2018-08-25 | 2019-01-15 | 咪付(广州)网络科技有限公司 | A kind of ticket-checked device and method based on recognition of face |
CN109345437A (en) * | 2018-08-31 | 2019-02-15 | 无感通圆(武汉)科技有限公司 | Open convenient subway station system and application by bus |
CN109409297A (en) * | 2018-10-30 | 2019-03-01 | 咪付(广西)网络技术有限公司 | A kind of personal identification method based on binary channels convolutional neural networks |
-
2019
- 2019-03-18 CN CN201910205499.2A patent/CN109977645A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102811222A (en) * | 2012-08-09 | 2012-12-05 | 浪潮电子信息产业股份有限公司 | Identity identification security method based on cloud computing |
CN105335750A (en) * | 2014-06-11 | 2016-02-17 | 数伦计算机技术(上海)有限公司 | Client identity identification system and identification method |
WO2016112630A1 (en) * | 2015-01-12 | 2016-07-21 | 芋头科技(杭州)有限公司 | Image recognition system and method |
WO2017181769A1 (en) * | 2016-04-21 | 2017-10-26 | 腾讯科技(深圳)有限公司 | Facial recognition method, apparatus and system, device, and storage medium |
CN107247941A (en) * | 2017-06-22 | 2017-10-13 | 易容智能科技(苏州)有限公司 | The sampling of accurate face and recognition methods of a kind of high hardware resiliency |
CN107978051A (en) * | 2017-12-15 | 2018-05-01 | 亿城通智能科技(大冶)有限公司 | A kind of access control system and method based on recognition of face |
CN207909166U (en) * | 2018-03-09 | 2018-09-25 | 广东万峯信息科技有限公司 | Public transport based on face recognition technology is pursued and captured an escaped prisoner system |
CN109215139A (en) * | 2018-08-25 | 2019-01-15 | 咪付(广州)网络科技有限公司 | A kind of ticket-checked device and method based on recognition of face |
CN109345437A (en) * | 2018-08-31 | 2019-02-15 | 无感通圆(武汉)科技有限公司 | Open convenient subway station system and application by bus |
CN109409297A (en) * | 2018-10-30 | 2019-03-01 | 咪付(广西)网络技术有限公司 | A kind of personal identification method based on binary channels convolutional neural networks |
Non-Patent Citations (1)
Title |
---|
彭冬鸣 等: "人脸识别技术在AFC系统中的应用", 《电子世界》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111031125A (en) * | 2019-12-10 | 2020-04-17 | 咪付(广西)网络技术有限公司 | User data pushing method and system based on travel record |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6787391B2 (en) | Face matching system, face matching method, and program | |
CN110491004A (en) | A kind of residential communities personnel security management system and method | |
CN109345437A (en) | Open convenient subway station system and application by bus | |
JP2022040245A (en) | Face collation system, face collation device, face collation method, and recording medium | |
CN104504408A (en) | Human face identification comparing method and system for realizing the method | |
CN109859366A (en) | A kind of subway of identity-based identification crosses brake system | |
CN104091176A (en) | Technology for applying figure and head portrait comparison to videos | |
CN202197300U (en) | Mobile face identification system | |
CN106203393A (en) | A kind of face collection and recognition method and the system realizing the method | |
WO2020230340A1 (en) | Facial recognition system, facial recognition method, and facial recognition program | |
CN110244846A (en) | Man-machine interaction method based on classroom aided education intellectualizing system | |
US20210006558A1 (en) | Method, apparatus and system for performing authentication using face recognition | |
CN110348331A (en) | Face identification method and electronic equipment | |
CN109544754A (en) | A kind of guard method and system based on recognition of face, computer equipment | |
CN110516623A (en) | A kind of face identification method, device and electronic equipment | |
CN110544333B (en) | Access control system and control method thereof | |
CN209118424U (en) | Utilize the client identity identifying system of the withdrawal circulation all-in-one machine of recognition of face | |
US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
CN109977645A (en) | A kind of identification system | |
US20230259962A1 (en) | Information processing device, face authentication promotion system, information processing method, non-transitory computer readable medium storing program | |
CN209471486U (en) | A kind of subway of identity-based identification crosses brake system | |
CN109949465A (en) | Unmanned intelligent barrier gate crosses machine system | |
CN208673384U (en) | Ticketing service processing system out of the station | |
CN105893994A (en) | Face recognition system | |
CN212181523U (en) | Subway is personal identification system for ticket checking |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190705 |