CN102075329B - Method for identifying user images - Google Patents

Method for identifying user images Download PDF

Info

Publication number
CN102075329B
CN102075329B CN 201110025179 CN201110025179A CN102075329B CN 102075329 B CN102075329 B CN 102075329B CN 201110025179 CN201110025179 CN 201110025179 CN 201110025179 A CN201110025179 A CN 201110025179A CN 102075329 B CN102075329 B CN 102075329B
Authority
CN
China
Prior art keywords
user
subscription client
background server
response message
consistent
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.)
Expired - Fee Related
Application number
CN 201110025179
Other languages
Chinese (zh)
Other versions
CN102075329A (en
Inventor
曾美霞
Original Assignee
Ningbo Shengyuan Technology Transmission Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo Shengyuan Technology Transmission Co Ltd filed Critical Ningbo Shengyuan Technology Transmission Co Ltd
Priority to CN 201110025179 priority Critical patent/CN102075329B/en
Publication of CN102075329A publication Critical patent/CN102075329A/en
Application granted granted Critical
Publication of CN102075329B publication Critical patent/CN102075329B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention provides a method for identifying user images, comprising the following steps: starting an authentication program by a user; connecting a user client with a backend server so as to authenticate the user; after successfully authenticating, starting a shooting device, and transmitting shot photos to the backend server for comparision; if the comparing results are inconsistent, starting an audio device and transmitting the recorded frequency to the backend server for comparision; if the comparing results of the photos or the comparing results of the audio frequency are consistent, shooting the photos of actions appointed by the user and then transmitting to the backend server for comparision; and if the comparing results are consistent, prompting the user that the authentication is successful. By utilizing the method provided by the iinvention, the problem that the image authentication of the user cannot be identified correctly caused by manufacturing false photos or changing appearances.

Description

A kind of user images recognition methods
Technical field
The present invention relates to network communications technology field, relate in particular to a kind of method of the user being carried out image recognition.
Background technology
Along with Internet development, there is increasing application scenario to need the identity of authenticated.A common example is exactly all kinds of social network sites, need judge in these websites whether the photo that the user uploads is my photo.A kind of authentication mode relatively more commonly used is user images identification; Usually computer system can require the user at first to upload the live photo of oneself; And then with some video photo upload of camera shooting; Contrast living photo and video photograph on the backstage, website by the customer service personnel, thereby judge whether video takes is user's picture.General as long as the photo that photo that the user uploads and camera are taken is enough clear, this user can pass through video authentication.
Yet the inventor finds that there is following shortcoming in above-mentioned existing user images recognition technology: at first, depend on artificial judgement; Workload is bigger, thereby cost is than higher, and the cycle of artificial judgement is long; Authentication speed is slow, and generally the user can't obtain authentication result in real time; Secondly; The photo that photo of only user being uploaded and camera are taken compares; Can not overcome the problem that the user plays tricks to the photo of taking; And if the user can't realize correct authentication because of subjectivity or objective reason make have caused the change of appearance with traditional user images recognition methods.
Summary of the invention
Technical problem to be solved by this invention is the deficiency that overcomes prior art, provides a more perfect user images recognition methods to come effectively to carry out authentification of user.
This technical scheme realizes that through subscription client, camera head, recording device and background server this method may further comprise the steps:
A. the user starts authentication procedure through subscription client;
B. subscription client inserts the user password dish through interactive interface prompting user, and after the load operation that detects the user password dish, subscription client is entered password through interactive interface prompting user; After the user correctly entered password, subscription client read the ID stored in the user password dish, user contact method, user base image and user's commonly used elementary audio, set up with background server between be connected; And the information that reads sent to background server, background server is searched corresponding record according to ID in database, and whether consistent in the more above-mentioned information that reads and the respective record; If it is consistent; Then accomplish authentication operations, return authentication success response message, execution in step C to subscription client; If inconsistent, execution in step G then
C. subscription client is after receiving authentication success response message; Start camera head; And the prompting user faces pick-up lens, subscription client extract institute take a picture in facial parts and send to background server, background server compares the base image of take a picture with the user; If both are inconsistent; Then background server returns inconsistent response message to subscription client, and execution in step D, if both are consistent; Then return consistent response message, and execution in step E;
D. subscription client is after receiving inconsistent response message; Start recording device, and a word that explicit user need be said on screen, after accomplishing recording; Subscription client sends to background server with voice data; Background server compares the elementary audio of record frequency with the user, if both are inconsistent, then background server returns inconsistent response message to subscription client; And execution in step G; If both are consistent, then return consistent response message, and execution in step E;
E. subscription client is after receiving consistent response message; The prompting user faces camera and closes left eye; After taking pictures; Point out the user to face camera once more and cover left eye with hand; And take pictures once more, subscription client sends to background server with the photo and the corresponding action instruction of taking, and background server is discerned according to the action command comparison film; If consistent, then return consistent response message;
F. subscription client is after receiving consistent response message, and the prompting authentification of user is successful;
G. finish authentication procedure.
The invention has the beneficial effects as follows: accomplish the contrast identification work to image owing to introduced the strong background server of data-handling capacity, solved tional identification and depended on artificial judgement, workload is big, and the judgement cycle is long, the slow-footed shortcoming of authentication; Simultaneously,, overcome the user and caused the change of appearance, and can't accomplish the problem of identification because of subjectivity or objective reason make through contrast that image and audio frequency are combined, raising further the reliability of authentication.
Step D in the said method further comprises:
If D1. consistent, then upgrade the information in the background server database, user's face-image of taking is preserved as user's base image, return the renewal response message to subscription client simultaneously;
D2. subscription client is after receiving the renewal response message, and the prompting user upgrades the user's in the user password dish base image;
Step e in the said method further comprises:
If E1. inconsistent, repeated execution of steps E then, if the result of three execution in step E is inconsistent, execution in step G then.
Step G in the said method further comprises:
G1. trigger corresponding early warning mechanism, according to user's contact method commonly used, send SMS to the user, the authentication operation from non-user has taken place in prompting.
Description of drawings
Fig. 1 is the operating process block diagram of a kind of user images recognition methods of the present invention.
Fig. 2 is a system architecture diagram of the present invention.
Embodiment
For making the object of the invention, technical scheme and advantage clearer, the present invention is made further detailed description below in conjunction with accompanying drawing.
Referring to Fig. 1 and Fig. 2, the present invention is a kind of user images recognition methods, mainly realizes associative operation through subscription client, camera head, recording device and background server:
A. the user starts authentication procedure through subscription client;
The user can open the camera head of installing in the subscription client earlier before starting authentication procedure, regulate the various parameters of this camera head, guaranteed the quality of taking pictures;
B. subscription client inserts the user password dish by interactive interface prompting user, and after the load operation that detects the user password dish, subscription client is entered password by interactive interface prompting user; After the user correctly enters password; Subscription client reads the ID of storing in the user password dish; The user uses contact method always; User base image and user's elementary audio; Set up with background server between be connected; And the information that reads sent to background server; Background server is searched corresponding record according to ID in database; And whether consistent in the more above-mentioned information that reads and the respective record; If it is consistent; Then accomplish authentication operations; Return authentication success response message to subscription client; Execution in step C, if inconsistent, execution in step G then;
C. subscription client is after receiving authentication success response message; Start camera head; And the prompting user faces pick-up lens; The user can repeat to take this photo; To obtain the most satisfied photo effect; Then; Subscription client extract institute take a picture in facial parts and send to background server; Background server compares the base image of take a picture with the user, if both are inconsistent, then background server returns inconsistent response message to subscription client; And execution in step D; If both are consistent, then return consistent response message, and execution in step E;
In practical application, above-mentioned camera head can adopt the video capture camera based on Flash, also can adopt other video capture instrument, control or software.Above-mentioned size of taking pictures can be set at 240*240 or bigger, thereby farthest obtains user profile.
Background server judges at first whether the quality of above-mentioned photo is qualified after obtaining the user picture of taking, mainly be to distinguish through the exposure of analyzing this initial photo whether photo is clear, and over-exposed photo or dark excessively photo will be regarded as defective.After judging that above-mentioned photo is defective, background server can notify the user to take a clear photograph again through subscription client.
D. subscription client is after receiving inconsistent response message; Start recording device; And a word that explicit user need be said on screen; Content in the user base audio frequency of this content in short and preservation is identical; After accomplishing recording; Subscription client sends to background server with voice data; The user can repeat to record this audio frequency, and to obtain the most satisfied audio frequency effect, background server compares the elementary audio of record frequency with the user; If both are inconsistent; Then background server returns inconsistent response message to subscription client, and execution in step G, if both are consistent; Then return consistent response message, and execution in step E;
Background server judges at first whether the quality of this audio frequency is qualified after obtaining the audio frequency of recording, mainly be the background noise through analyzing audio, and the audio frequency that background noise is strong excessively will be regarded as defective.After judging that above-mentioned audio frequency is defective, background server can notify the user to record a section audio again through subscription client.
If D1. consistent, then upgrade the information in the background server database, user's face-image of taking is preserved as user's base image, return the renewal response message to subscription client simultaneously;
D2. subscription client is after receiving the renewal response message, and the prompting user upgrades the user's in the user password dish base image; The user can comment effective certificate to handle the business of upgrading base image to the sales counter or the site of appointment;
E. subscription client is after receiving consistent response message; The prompting user faces camera and closes left eye; After taking pictures; Point out the user to face camera once more and cover left eye with hand; And take pictures once more, subscription client sends to background server with the photo and the corresponding action instruction of taking, and background server is discerned according to the action command comparison film; If consistent, then return consistent response message;
If E1. inconsistent, repeated execution of steps E then, if the result of three execution in step E is inconsistent, execution in step G then;
F. subscription client is after receiving consistent response message, and the prompting authentification of user is successful;
G. finish authentication procedure;
G1. trigger corresponding early warning mechanism, according to user's contact method commonly used, send SMS to the user, the authentication operation from non-user has taken place in prompting.
In practical application, can many people carry out the image recognition operation simultaneously, and, can the user number of request authentication be limited in order to guarantee the speed of user images authentication.Subscription client total number to submitting authentication request to is provided with a threshold value, and when reaching this threshold value, subscription client can't submit to authentication request to arrive background server.At this moment, subscription client will be reminded the current peak hours/period just of user, have many people waiting for image authentication, please try after a while again.The number of above-mentioned subscription client is corresponding with number of users.
Obviously, it is apparent to those skilled in the art that above-mentioned each step of the present invention can realize with the general calculation device; They can concentrate on the single calculation element; Perhaps be distributed on the network that a plurality of calculation element forms, alternatively, they can be realized with the executable program code of calculation element; Thereby; Can they be stored in the storage device and carry out, perhaps they are made into each integrated circuit modules respectively, perhaps a plurality of modules in them or step are made into the single integrated circuit module and realize by calculation element.Like this, the present invention is not restricted to any specific hardware and software combination.
The above is merely the preferred embodiments of the present invention, is not limited to the present invention, and for a person skilled in the art, the present invention can have various changes and variation.All within spirit of the present invention and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (4)

1. a user images recognition methods is characterized in that: comprise the following steps: at least
A. the user starts authentication procedure through subscription client;
B. subscription client inserts the user password dish by interactive interface prompting user, and after the load operation that detects the user password dish, subscription client is entered password by interactive interface prompting user; After the user correctly enters password; Subscription client reads the ID of storing in the user password dish; The user uses contact method always; User base image and user's elementary audio; Set up with background server between be connected; And the information that reads sent to background server; Background server is searched corresponding record according to ID in database; And whether consistent in the more above-mentioned information that reads and the respective record; If it is consistent; Then accomplish authentication operations; Return authentication success response message to subscription client; Execution in step C, if inconsistent, execution in step G then;
C. subscription client is after receiving authentication success response message; Start camera head, and the prompting user faces pick-up lens, the subscription client extraction middle facial parts of taking a picture; And send to background server; Background server compares the base image of take a picture with the user, if both are inconsistent, then background server returns inconsistent response message to subscription client; And execution in step D; If both are consistent, then return consistent response message, and execution in step E;
D. subscription client is after receiving inconsistent response message; Start recording device, and a word that explicit user need be said on screen, after accomplishing recording; Subscription client sends to background server with voice data; Background server compares the elementary audio of record frequency with the user, if both are inconsistent, then background server returns inconsistent response message to subscription client; And execution in step G; If both are consistent, then return consistent response message, and execution in step E;
E. subscription client is after receiving consistent response message; The prompting user faces camera and closes left eye; After taking pictures; The prompting user faces camera and covers left eye with hand; And take pictures once more, subscription client sends to background server with the photo and the corresponding action instruction of taking, and background server is discerned according to the action command comparison film; If consistent, then return consistent response message;
F. subscription client is after receiving consistent response message, and the prompting authentification of user is successful;
G. finish authentication procedure.
2. according to the user images recognition methods described in the claim 1, it is characterized in that: said step D further comprises:
If D1. consistent, then upgrade the information in the background server database, user's face-image of taking is preserved as user's base image, return the renewal response message to subscription client simultaneously;
D2. subscription client is after receiving the renewal response message, and the prompting user upgrades the user's in the user password dish base image.
3. according to described user images recognition methods one of in the claim 1 to 2, it is characterized in that: said step e further comprises:
If E1. inconsistent, repeated execution of steps E then, if the result of three execution in step E is inconsistent, execution in step G then.
4. according to described user images recognition methods one of in the claim 1 to 2, it is characterized in that: said step G further comprises:
G1. trigger corresponding early warning mechanism, according to user's contact method commonly used, send SMS to the user, the authentication operation from non-user has taken place in prompting.
CN 201110025179 2011-01-21 2011-01-21 Method for identifying user images Expired - Fee Related CN102075329B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110025179 CN102075329B (en) 2011-01-21 2011-01-21 Method for identifying user images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201110025179 CN102075329B (en) 2011-01-21 2011-01-21 Method for identifying user images

Publications (2)

Publication Number Publication Date
CN102075329A CN102075329A (en) 2011-05-25
CN102075329B true CN102075329B (en) 2012-06-13

Family

ID=44033685

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110025179 Expired - Fee Related CN102075329B (en) 2011-01-21 2011-01-21 Method for identifying user images

Country Status (1)

Country Link
CN (1) CN102075329B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106210230B (en) * 2016-06-29 2019-10-08 努比亚技术有限公司 A kind of contact person increases method and terminal
CN107180465A (en) * 2017-05-11 2017-09-19 深圳市柘叶红实业有限公司 Turnover personnel and article record terminal system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7535496B2 (en) * 2002-01-30 2009-05-19 Intel Corporation Audio-based attention grabber for imaging devices
US7594680B2 (en) * 2004-06-03 2009-09-29 Datacard Corporation Identification documents with enhanced security
CN101753307B (en) * 2009-12-31 2015-08-12 马宇尘 The system of communication terminal user authentication and method of operation

Also Published As

Publication number Publication date
CN102075329A (en) 2011-05-25

Similar Documents

Publication Publication Date Title
JP6743188B2 (en) Remote contract interview method, electronic device, and computer-readable storage medium
US9288196B2 (en) Identity verification via selection of sensible output from recorded digital data
CN105516085B (en) A kind of system and method managing the interim internet behavior of visitor
CN106710017B (en) Identity verification method, device and system for logistics signing
WO2022022493A1 (en) Image authenticity determination method and system
CN104835266A (en) Business handling method and system of VTM
CN110414376B (en) Method for updating face recognition model, face recognition camera and server
JP6969663B2 (en) Devices and methods for identifying the user's imaging device
CN103279764A (en) Real-name network authentication system based on face identification
CN107622246B (en) Face recognition method and related product
CN110247898B (en) Identity verification method, identity verification device, identity verification medium and electronic equipment
WO2023173686A1 (en) Detection method and apparatus, electronic device, and storage medium
CN112199530B (en) Multi-dimensional face library picture automatic updating method, system, equipment and medium
CN109005104A (en) A kind of instant communicating method, device, server and storage medium
CN114387548A (en) Video and liveness detection method, system, device, storage medium and program product
CN112989308B (en) Account authentication method, device, equipment and medium
CN102075329B (en) Method for identifying user images
CN106998332A (en) Safe login method, device, storage medium and computer equipment
CN110837901A (en) Cloud test drive appointment auditing method and device, storage medium and cloud server
CN113516167A (en) Biological feature recognition method and device
US20230116291A1 (en) Image data processing method and apparatus, device, storage medium, and product
CN110866418B (en) Image base generation method, device, equipment, system and storage medium
CN114387674A (en) Living body detection method, living body detection system, living body detection apparatus, storage medium, and program product
WO2022222957A1 (en) Method and system for identifying target
WO2022222735A1 (en) Information processing method and apparatus, computer device, and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Ma Qianli

Inventor before: Zeng Meixia

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20170322

Address after: 301500 Chaoyang building, Ninghe District, Tianjin 18-2-301

Patentee after: Ma Qianli

Address before: 315192 Ningbo, Yinzhou District Zhong Gong Temple Street, Temple Road, No. 285

Patentee before: Ningbo Shengyuan Technology Transmission Co., Ltd.

CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20120613

Termination date: 20180121