CN104573632A - Three-dimensional face identification method for depositing and withdrawing money in bank - Google Patents

Three-dimensional face identification method for depositing and withdrawing money in bank Download PDF

Info

Publication number
CN104573632A
CN104573632A CN201410766911.5A CN201410766911A CN104573632A CN 104573632 A CN104573632 A CN 104573632A CN 201410766911 A CN201410766911 A CN 201410766911A CN 104573632 A CN104573632 A CN 104573632A
Authority
CN
China
Prior art keywords
feature
region
image
dimensional face
depositing
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
Application number
CN201410766911.5A
Other languages
Chinese (zh)
Inventor
张会林
孙利华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Fufeng Technology Co Ltd
Original Assignee
Suzhou Fufeng Technology 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 Suzhou Fufeng Technology Co Ltd filed Critical Suzhou Fufeng Technology Co Ltd
Priority to CN201410766911.5A priority Critical patent/CN104573632A/en
Publication of CN104573632A publication Critical patent/CN104573632A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/64Three-dimensional objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/165Detection; Localisation; Normalisation using facial parts and geometric relationships

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Collating Specific Patterns (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention relates to the technical field of face identification, in particular to a three-dimensional face identification method for depositing and withdrawing money in a bank. The method comprises the following steps: pre-constructing an image feature database of a face and a neck of a bank customer; scanning the face and the neck once from front to back to obtain a first image, storing the first image, scanning the face and the neck once from top to bottom to obtain a second image, and storing the second image; integrating the first image and the second image by a processor module to obtain a three-dimensional face image; carrying out regional feature extraction on the three-dimensional face image, and constructing a feature of a region I, a feature of a region II, a feature of a region III and a feature of a region IV; carrying out multi-channel parallel comparison on the features with the image feature database. The three-dimensional face identification method disclosed by the invention has the benefits that due to three-dimensional face identification, no queuing service is needed; identity verification is finished by face identification via machine, and the services of depositing and withdrawing the money in the bank can be handled; the three-dimensional face identification method is very convenient.

Description

For the three-dimensional face identification method of depositing and drawing in bank
Technical field
The present invention relates to technical field of face recognition, be specifically related to a kind of three-dimensional face identification method for depositing and drawing in bank.
Background technology
Current three-dimensional face recognition technology is mainly used in work attendance, access field, and depositing and drawing in bank especially handle the business such as surely to deposit time, usually need Zero queuing to handle, comparatively bother and need attendant's assist process of sales counter, manpower consumption is large.
Summary of the invention
The object of the invention is to overcome the problems referred to above, provide a kind of and save time and the three-dimensional face identification method for depositing and drawing in bank of manpower.
To achieve these goals, the technical solution adopted in the present invention is: for the three-dimensional face identification method of depositing and drawing in bank, it is characterized in that, comprise the steps:
(1) face of bank client and the image feature base of neck is set up in advance;
(2) face and neck is scanned, from front to back run-down be stored as the first image, then run-down be stored as the second image from top to bottom; The described ear referred to from front to back from the nose of people to people;
(3) be three-dimensional face images by processor module by the first image and the second image integration;
(4) subregion feature extraction is carried out to above-mentioned three-dimensional face images, set up the feature in region one, the feature in region two, the feature in region three, the feature in region four; And carry out multi-channel parallel comparison with image feature base;
(5) in the feature in region one to four, do not have aspect ratio to success or only have 1 aspect ratio to success, then this characteristic storage extracted is entered image feature base, and the feature in this region one to four of extracting being logically interrelated;
(6) in the feature in region one to four, there are 2 aspect ratios to success, then get back to step (2);
(7) in the feature in region one to four, have a 3-4 aspect ratio to success, then recognition of face completes.
The aforesaid three-dimensional face identification method for depositing and drawing in bank, in step (4), region one is respectively shape of face, nose, face, neck to region four.
The aforesaid three-dimensional face identification method for depositing and drawing in bank, in step (4), described multi-channel parallel comparison adopts FPGA processor to realize.
The aforesaid three-dimensional face identification method for depositing and drawing in bank, carries out human face scanning by the scanner being arranged on diverse location simultaneously.
The aforesaid three-dimensional face identification method for depositing and drawing in bank, in step (5), the interrelated feature referring to region one to four integrally in logic, should jointly and image feature base comparison.
The aforesaid three-dimensional face identification method for depositing and drawing in bank, by storage unit store images property data base.
To the invention has the beneficial effects as follows: by three-dimensional face identification, without the need to Zero queuing, complete authentication by machine recognition of face, then can handle the business such as depositing and drawing in bank, very convenient.
Embodiment
Below in conjunction with specific embodiment, the invention will be further described.
For the three-dimensional face identification method of depositing and drawing in bank, it is characterized in that, comprise the steps:
(1) face of bank client and the image feature base of neck is set up in advance;
(2) face and neck is scanned, from front to back run-down be stored as the first image, then run-down be stored as the second image from top to bottom; The described ear referred to from front to back from the nose of people to people;
(3) be three-dimensional face images by processor module by the first image and the second image integration;
(4) subregion feature extraction is carried out to above-mentioned three-dimensional face images, set up the feature in region one, the feature in region two, the feature in region three, the feature in region four; And carry out multi-channel parallel comparison with image feature base;
(5) in the feature in region one to four, do not have aspect ratio to success or only have 1 aspect ratio to success, then this characteristic storage extracted is entered image feature base, and the feature in this region one to four of extracting being logically interrelated;
(6) in the feature in region one to four, there are 2 aspect ratios to success, then get back to step (2);
(7) in the feature in region one to four, have a 3-4 aspect ratio to success, then recognition of face completes.
In step (4), region one is respectively shape of face, nose, face, neck to region four.
In step (4), described multi-channel parallel comparison adopts FPGA processor to realize.
Carry out human face scanning by the scanner being arranged on diverse location simultaneously.
In step (5), the interrelated feature referring to region one to four integrally in logic, should jointly and image feature base comparison.
By storage unit store images property data base.
Above-described embodiment does not limit the present invention in any form, the technical scheme that the mode that all employings are equal to replacement or equivalent transformation obtains, and all drops on protection scope of the present invention.

Claims (6)

1. for the three-dimensional face identification method of depositing and drawing in bank, it is characterized in that, comprise the steps:
Set up the face of bank client and the image feature base of neck in advance;
Scanning face and neck, from front to back run-down be stored as the first image, then run-down be stored as the second image from top to bottom; The described ear referred to from front to back from the nose of people to people;
Be three-dimensional face images by processor module by the first image and the second image integration;
Subregion feature extraction is carried out to above-mentioned three-dimensional face images, sets up the feature in region one, the feature in region two, the feature in region three, the feature in region four; And carry out multi-channel parallel comparison with image feature base;
In the feature in region one to four, do not have aspect ratio to success or only have 1 aspect ratio to success, then this characteristic storage extracted is entered image feature base, and the feature in this region one to four of extracting being logically interrelated;
In the feature in region one to four, there are 2 aspect ratios to success, then get back to step (2);
In the feature in region one to four, have a 3-4 aspect ratio to success, then recognition of face completes.
2. the three-dimensional face identification method for depositing and drawing in bank according to claim 1, is characterized in that, in step (4), region one is respectively shape of face, nose, face, neck to region four.
3. the three-dimensional face identification method for depositing and drawing in bank according to claim 1, is characterized in that, in step (4), described multi-channel parallel comparison adopts FPGA processor to realize.
4. the three-dimensional face identification method for depositing and drawing in bank according to claim 1, is characterized in that, carries out human face scanning by the scanner being arranged on diverse location simultaneously.
5. the three-dimensional face identification method for depositing and drawing in bank according to claim 1, is characterized in that, in step (5), the interrelated feature referring to region one to four integrally in logic, should jointly and image feature base comparison.
6. the three-dimensional face identification method for depositing and drawing in bank according to claim 1, is characterized in that, by storage unit store images property data base.
CN201410766911.5A 2014-12-15 2014-12-15 Three-dimensional face identification method for depositing and withdrawing money in bank Pending CN104573632A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410766911.5A CN104573632A (en) 2014-12-15 2014-12-15 Three-dimensional face identification method for depositing and withdrawing money in bank

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410766911.5A CN104573632A (en) 2014-12-15 2014-12-15 Three-dimensional face identification method for depositing and withdrawing money in bank

Publications (1)

Publication Number Publication Date
CN104573632A true CN104573632A (en) 2015-04-29

Family

ID=53089655

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410766911.5A Pending CN104573632A (en) 2014-12-15 2014-12-15 Three-dimensional face identification method for depositing and withdrawing money in bank

Country Status (1)

Country Link
CN (1) CN104573632A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204711A (en) * 2016-06-29 2016-12-07 深圳开立生物医疗科技股份有限公司 A kind of three dimensional volumetric image processing method and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101145261A (en) * 2007-10-11 2008-03-19 中国科学院长春光学精密机械与物理研究所 ATM system automatic recognition device
CN101751562A (en) * 2009-12-28 2010-06-23 镇江奇点软件有限公司 Bank transaction image forensic acquiring method based on face recognition
CN102262727A (en) * 2011-06-24 2011-11-30 常州锐驰电子科技有限公司 Method for monitoring face image quality at client acquisition terminal in real time
CN104063690A (en) * 2014-06-25 2014-09-24 广州卓腾科技有限公司 Identity authentication method based on face recognition technology, device thereof and system thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101145261A (en) * 2007-10-11 2008-03-19 中国科学院长春光学精密机械与物理研究所 ATM system automatic recognition device
CN101751562A (en) * 2009-12-28 2010-06-23 镇江奇点软件有限公司 Bank transaction image forensic acquiring method based on face recognition
CN102262727A (en) * 2011-06-24 2011-11-30 常州锐驰电子科技有限公司 Method for monitoring face image quality at client acquisition terminal in real time
CN104063690A (en) * 2014-06-25 2014-09-24 广州卓腾科技有限公司 Identity authentication method based on face recognition technology, device thereof and system thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
卢春雨等: "基于区域特征的快速人脸检测法", 《万方数据》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204711A (en) * 2016-06-29 2016-12-07 深圳开立生物医疗科技股份有限公司 A kind of three dimensional volumetric image processing method and system
CN106204711B (en) * 2016-06-29 2020-12-18 深圳开立生物医疗科技股份有限公司 Three-dimensional volume image processing method and system

Similar Documents

Publication Publication Date Title
CN107833341B (en) Intelligent queuing method, equipment and computer readable storage medium
CN107239725B (en) Information display method, device and system
CN105069622B (en) A kind of face recognition payment system and method for facing moving terminal
CN102968827A (en) Human face identification security and protection attendance system based on cloud data processing bank
CN101901461A (en) Bank VIP customer service system with intelligent face recognition and method
CN104915795A (en) Hotel self-help check-in management system and hotel self-help check-in management method
CN204010137U (en) Bank business self-service automatic teller machine
CN104751321A (en) Intelligent bus payment system with specific people recognition function and implementing method of intelligent bus payment system
CN105893948A (en) Method and apparatus for face identification in video conference
CN105335750A (en) Client identity identification system and identification method
CN108038693A (en) The consistent method and system of automatic vending machine identification adult customer's testimony of a witness
CN206672186U (en) A kind of meeting signature system
CN201142097Y (en) Anti-counterfeiting safety queuing device based on biological recognition technology
CN109272671A (en) A method of based on the local locker in real time of the multiselect of recognition of face and fingerprint recognition and its carrying out access article
CN108319941A (en) Electricity consumption business handling auxiliary system based on recognition of face
CN111445252A (en) Method, device and equipment for establishing biological feature library
CN103685197A (en) Client information acquisition method and server
CN115294523A (en) E-commerce cargo monitoring and analyzing cloud platform based on Internet of things
CN211180928U (en) Information processing apparatus, express delivery management system, and information processing system
CN107025558A (en) A kind of transaction system and transaction processing method
CN104573632A (en) Three-dimensional face identification method for depositing and withdrawing money in bank
CN106127877B (en) A kind of meeting scene based on custom model is registered method
CN111047796A (en) Deposit and withdrawal method and system based on face recognition
CN109117414A (en) Self-service query integrated machine system and implementation method for people's livelihood archives
CN104408616A (en) Supermarket prepayment method based on three-dimensional face recognition

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20150429

RJ01 Rejection of invention patent application after publication