CN104408417A - Supermarket prepayment method based on three-dimensional face local feature matching - Google Patents
Supermarket prepayment method based on three-dimensional face local feature matching Download PDFInfo
- Publication number
- CN104408417A CN104408417A CN201410684312.9A CN201410684312A CN104408417A CN 104408417 A CN104408417 A CN 104408417A CN 201410684312 A CN201410684312 A CN 201410684312A CN 104408417 A CN104408417 A CN 104408417A
- Authority
- CN
- China
- Prior art keywords
- supermarket
- image
- local feature
- point
- dimensional
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a supermarket prepayment method based on three-dimensional face local feature matching. The supermarket prepayment method is characterized by including the steps of S01, establishing a prepayment face recognition base; S02, adopting a three-dimensional laser scanner to collect face images; S03, subjecting the face images to graying; S04, employing a feature detector to select key local areas from the images; S05, extracting a certain invariant features from the local areas; S06, matching the local areas extracted from the images by employing appropriate distance measurement and matching algorithm; S07, if point-to-point matching ratio excesses a matching threshold value, entering the supermarket prepayment system, otherwise, the payment fails. The supermarket prepayment method has the advantages that without a shopping card, the three-dimensional face recognition prepayment is realized, three-dimensional face recognition corresponding speed is fast, safety is high, calculation is simple, operation efficiency is high, and adaption to the intelligent payment field is available.
Description
Technical field
The invention belongs to intelligent payment technical field, particularly relate to a kind of supermarket prepaid payment method based on three-dimensional face local feature coupling.
Background technology
At present, supermarket distribution purchase card, realize pre-payment by brush purchase card, need terminal magnetic card swiping terminal and purchase card with the use of, after purchase card is lost, economic loss is produced to client, prior art, three-dimensional face identification generally carries out image zooming-out, calculation of complex based on neural network or mathematics prior probability, operation time is long, can only payment technical field can not apply.
Summary of the invention
In order to solve prior art problem, the invention provides a kind of supermarket prepaid payment method based on three-dimensional face local feature coupling, departing from purchase card itself and realizing the payment of three-dimensional face identification pre-payment, three-dimensional face identification corresponding speed is fast, security performance is high, and calculate simple, efficiency is high.
The technical solution used in the present invention is: a kind of supermarket prepaid payment method based on three-dimensional face local feature coupling, comprises the following steps,
S01, sets up pre-payment recognition of face storehouse: the face master sample view data obtained by three-dimensional laser scanner, is deposited in database by described sample image data, sets up recognition of face storehouse;
View data is cloud data, and scan-data stores with cloud data form, and store black and white facial image, the information of each point comprises three-dimensional space position, relative coordinate system position and half-tone information.
S02, three-dimensional laser scanner gathers facial image;
S03, carries out gray processing process by the facial image that step S02 obtains;
S04, uses property detector from image, select crucial regional area;
Property detector described in step S04 comprises Corner Detection device, spot detection device, area detector.
Corner Detection device is based on edge link and segmentation detected image edge; Spot detection device detects face's eyes, nose, face feature based on difference of Gaussian; Area detector detects the connected region in image by auto-thresholding algorithm.
S05, the regional area detected from step S04 extracts has Vertic features scarcely, realizes local feature and detects;
Step S05 specifically comprises the following steps:
(501) supporting zone is normalized;
(502) image denoising, image scaling and rim detection is carried out based on B-spline function;
(503) using metric space as multi-scale Representation, realize multiple dimensioned constant local feature and detect;
(504) position that 3 × 3 × 3 three-dimensional extremum extracting go out point of interest is searched for.
S06, uses suitable distance metric and matching algorithm to mate the local feature extracted in image: based on the point-to-point coupling of overall geometric transformation information realization;
Step S06 specifically comprises the following steps:
(601) point-to-point coupling is realized based on RANSAC image matching algorithm;
(602) local feature is utilized slightly to mate;
(603) RANSAC algorithm is utilized to calculate the overall geometric transformation of image in recognition of face storehouse described in the facial image of Real-time Collection and step S01;
(604) match point between computed image.
S07, when the point-to-point matching rate of step S06 exceedes matching threshold, enters supermarket pre-payment payment system, otherwise, pay unsuccessfully.
Compared with prior art, beneficial effect of the present invention comprises:
The present invention departs from purchase card itself and realizes the payment of three-dimensional face identification pre-payment, and three-dimensional face identification corresponding speed is fast, and security performance is high, and calculate simple, operational efficiency is high, can promote the use of intelligent payment technical field.
Embodiment
Below in conjunction with specific embodiment, the present invention is further described.
Based on a supermarket prepaid payment method for three-dimensional face local feature coupling, comprise the following steps,
S01, sets up pre-payment recognition of face storehouse: the face master sample view data obtained by three-dimensional laser scanner, is deposited in database by described sample image data, sets up recognition of face storehouse;
View data is cloud data, and scan-data stores with cloud data form, and store black and white facial image, the information of each point comprises three-dimensional space position, relative coordinate system position and half-tone information.
S02, three-dimensional laser scanner gathers facial image;
S03, carries out gray processing process by the facial image that step S02 obtains;
S04, uses property detector from image, select crucial regional area;
Property detector described in step S04 comprises Corner Detection device, spot detection device, area detector.
Corner Detection device is based on edge link and segmentation detected image edge; Spot detection device detects face's eyes, nose, face feature based on difference of Gaussian; Area detector detects the connected region in image by auto-thresholding algorithm.
S05, the regional area detected from step S04 extracts has Vertic features scarcely, realizes local feature and detects;
Step S05 specifically comprises the following steps:
(501) supporting zone is normalized;
(502) image denoising, image scaling and rim detection is carried out based on B-spline function;
(503) using metric space as multi-scale Representation, realize multiple dimensioned constant local feature and detect;
(504) position that 3 × 3 × 3 three-dimensional extremum extracting go out point of interest is searched for.
S06, uses suitable distance metric and matching algorithm to mate the local feature extracted in image: based on the point-to-point coupling of overall geometric transformation information realization;
Step S06 specifically comprises the following steps:
(601) point-to-point coupling is realized based on RANSAC image matching algorithm;
(602) local feature is utilized slightly to mate;
(603) RANSAC algorithm is utilized to calculate the overall geometric transformation of image in recognition of face storehouse described in the facial image of Real-time Collection and step S01;
(604) match point between computed image.
S07, when the point-to-point matching rate of step S06 exceedes matching threshold, enters supermarket pre-payment payment system, otherwise, pay unsuccessfully.
Below be only the preferred embodiment of the present invention; be noted that for those skilled in the art; under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (6)
1., based on the supermarket prepaid payment method of three-dimensional face local feature coupling, it is characterized in that, comprise the following steps,
S01, sets up pre-payment recognition of face storehouse: the face master sample view data obtained by three-dimensional laser scanner, is deposited in database by described sample image data, sets up recognition of face storehouse;
S02, three-dimensional laser scanner gathers facial image;
S03, carries out gray processing process by the facial image that step S02 obtains;
S04, uses property detector from image, select crucial regional area;
S05, the regional area detected from step S04 extracts has Vertic features scarcely, realizes local feature and detects;
S06, uses suitable distance metric and matching algorithm to mate the local feature extracted in image: based on the point-to-point coupling of overall geometric transformation information realization;
S07, when the point-to-point matching rate of step S06 exceedes matching threshold, enters supermarket pre-payment payment system, otherwise, pay unsuccessfully.
2. the supermarket prepaid payment method based on three-dimensional face local feature coupling according to claim 1, it is characterized in that, view data described in step S01 is cloud data, scan-data stores with cloud data form, store black and white facial image, the information of each point comprises three-dimensional space position, relative coordinate system position and half-tone information.
3. the supermarket prepaid payment method based on three-dimensional face local feature coupling according to claim 1, it is characterized in that, property detector described in step S04 comprises Corner Detection device, spot detection device, area detector.
4. the supermarket prepaid payment method based on three-dimensional face local feature coupling according to claim 3, is characterized in that, described Corner Detection device is based on edge link and segmentation detected image edge; Spot detection device detects face's eyes, nose, face feature based on difference of Gaussian; Area detector detects the connected region in image by auto-thresholding algorithm.
5. the supermarket prepaid payment method based on three-dimensional face local feature coupling according to claim 1, it is characterized in that, step S05 specifically comprises the following steps:
(501) supporting zone is normalized;
(502) image denoising, image scaling and rim detection is carried out based on B-spline function;
(503) using metric space as multi-scale Representation, realize multiple dimensioned constant local feature and detect;
(504) position that 3 × 3 × 3 three-dimensional extremum extracting go out point of interest is searched for.
6. the supermarket prepaid payment method based on three-dimensional face local feature coupling according to claim 1, it is characterized in that, step S06 specifically comprises the following steps:
(601) point-to-point coupling is realized based on RANSAC image matching algorithm;
(602) local feature is utilized slightly to mate;
(603) RANSAC algorithm is utilized to calculate the overall geometric transformation of image in recognition of face storehouse described in the facial image of Real-time Collection and step S01;
(604) match point between computed image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410684312.9A CN104408417A (en) | 2014-11-25 | 2014-11-25 | Supermarket prepayment method based on three-dimensional face local feature matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410684312.9A CN104408417A (en) | 2014-11-25 | 2014-11-25 | Supermarket prepayment method based on three-dimensional face local feature matching |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104408417A true CN104408417A (en) | 2015-03-11 |
Family
ID=52646048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410684312.9A Pending CN104408417A (en) | 2014-11-25 | 2014-11-25 | Supermarket prepayment method based on three-dimensional face local feature matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104408417A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105243374A (en) * | 2015-11-02 | 2016-01-13 | 湖南拓视觉信息技术有限公司 | Three-dimensional human face recognition method and system, and data processing device applying same |
CN109034112A (en) * | 2018-08-18 | 2018-12-18 | 章云娟 | Reliable hospital face checkout mechanism |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101464948A (en) * | 2009-01-14 | 2009-06-24 | 北京航空航天大学 | Object identification method for affine constant moment based on key point |
WO2013005447A1 (en) * | 2011-07-07 | 2013-01-10 | 花王株式会社 | Face impression analysis method, cosmetic counseling method, and face image generation method |
-
2014
- 2014-11-25 CN CN201410684312.9A patent/CN104408417A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101464948A (en) * | 2009-01-14 | 2009-06-24 | 北京航空航天大学 | Object identification method for affine constant moment based on key point |
WO2013005447A1 (en) * | 2011-07-07 | 2013-01-10 | 花王株式会社 | Face impression analysis method, cosmetic counseling method, and face image generation method |
Non-Patent Citations (2)
Title |
---|
刘恒: ""3D及多视人耳识别关键技术研究"", 《中国博士学位论文全文数据库(信息科技辑)》 * |
宫明明: ""基于局部特征的图像匹配与识别"", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105243374A (en) * | 2015-11-02 | 2016-01-13 | 湖南拓视觉信息技术有限公司 | Three-dimensional human face recognition method and system, and data processing device applying same |
CN105243374B (en) * | 2015-11-02 | 2018-11-20 | 湖南拓视觉信息技术有限公司 | Three-dimensional face identification method, system and the data processing equipment using it |
CN109034112A (en) * | 2018-08-18 | 2018-12-18 | 章云娟 | Reliable hospital face checkout mechanism |
CN109034112B (en) * | 2018-08-18 | 2019-04-19 | 上海今创信息技术有限公司 | Hospital's face checkout system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108229427B (en) | Identity security verification method and system based on identity document and face recognition | |
CN104392220A (en) | Three-dimensional face recognition airport security inspection method based on cloud server | |
Soltany et al. | Fast and accurate pupil positioning algorithm using circular Hough transform and gray projection | |
CN102779274B (en) | Intelligent television face recognition method based on binocular camera | |
CN103077407B (en) | Car logo positioning and recognition method and car logo positioning and recognition system | |
CN103093201B (en) | Vehicle-logo location recognition methods and system | |
CN103914686A (en) | Face comparison authentication method and system based on identification photo and collected photo | |
US20130044914A1 (en) | Methods for detecting and recognizing a moving object in video and devices thereof | |
CN103208004A (en) | Automatic recognition and extraction method and device for bill information area | |
CN104751040A (en) | Fingerprint detection method based on intelligent mobile information equipment | |
Cho et al. | 2D barcode detection using images for drone-assisted inventory management | |
CN105575011A (en) | Intelligent iris payment machine | |
Saran et al. | Robust visual analysis for planogram compliance problem | |
Shen et al. | Adaptive pedestrian tracking via patch-based features and spatial–temporal similarity measurement | |
CN103745209A (en) | Human face identification method and system | |
CN109308436B (en) | Living body face recognition method based on active infrared video | |
CN104408616A (en) | Supermarket prepayment method based on three-dimensional face recognition | |
Halidou et al. | Fast pedestrian detection based on region of interest and multi-block local binary pattern descriptors | |
CN104408417A (en) | Supermarket prepayment method based on three-dimensional face local feature matching | |
CN104573628A (en) | Three-dimensional face recognition method | |
CN111476609A (en) | Retail data acquisition method, system, device and storage medium | |
EP3629228B1 (en) | Image processing for determining relationships between tracked objects | |
CN204347865U (en) | A kind of finger vein recognition terminal of banking system | |
Pise et al. | Text detection and recognition in natural scene images | |
Malathi et al. | Fingerprint pore extraction based on marker controlled watershed segmentation |
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: 20150311 |
|
RJ01 | Rejection of invention patent application after publication |