CN105894288A - Using method of supermarket face payment platform - Google Patents
Using method of supermarket face payment platform Download PDFInfo
- Publication number
- CN105894288A CN105894288A CN201610204443.1A CN201610204443A CN105894288A CN 105894288 A CN105894288 A CN 105894288A CN 201610204443 A CN201610204443 A CN 201610204443A CN 105894288 A CN105894288 A CN 105894288A
- Authority
- CN
- China
- Prior art keywords
- equipment
- image
- face
- identity
- iris
- 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.)
- Withdrawn
Links
Classifications
-
- 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
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Business, Economics & Management (AREA)
- Ophthalmology & Optometry (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a supermarket face payment platform comprising a customer face detection system, a payment system and a control system, wherein the customer face detection system is used for detecting the identity of a current checkout customer, and the control system is connected with the customer face detection system and the payment system and is used for making the payment system complete payment based on the identity of the customer output by the customer face detection system. Through the method, the efficiency of supermarket checkout is improved.
Description
Technical field
The present invention relates to face payment technical field, particularly relate to the user of a kind of supermarket face payment platform
Method.
Background technology
Recognition of face is the biological characteristic knowledge that a kind of Facial Features information based on people carries out authentication
Other technology, the maximum feature of technology is to be avoided that leakage of personal information, and uses non-contacting mode to enter
Row identifies.
Recognition of face and fingerprint recognition, personal recognition, retina identification, skeleton identification, heart beating identification
Etc. broadly falling into human body biological characteristics identification technology, all it is as photoelectric technology, micro-computer technology, figure
As the fast development of the technology such as treatment technology and pattern recognition is arisen at the historic moment.Can fast, precisely,
Wholesomely carry out identity identification;Having non-reproduction, even if having done cosmetic surgery, this technology also can
Find out from hundreds of face feature " originally you ".Face identification system application in the world is
Through the most extensive.
The developing history that recognition of face pays is as follows: in July, 2013, venture company of Finland Uniqul pushed away
Go out the payment platform based on face identification system of first item in history.Claim according to Uniqul, this technology
Having applied for a patent, he can greatly shorten the time of payment, and has the guarantor of " military level algorithm "
Protect.User's registration of Uniqul " brush face " payment system has been started up, first can be pungent in Finland Hull
Base command is disposed." brush face " system currently Helsinki is tested.For peace
The trade company of dress Uniqul, company's preliminary project provides free terminal unit.
But, existing recognition of face payment scheme still suffers from following deficiency: (1) is special due to face
Levying and can change due to face-lifting, the reason such as fat or thin, old and feeble, single dependence facial characteristics completes
Pay the payment difficulty problem inevitably bringing recognition failures and cause;(2) Gu of checkout is waited
The possible more than one of visitor, if carrying out face-image segmentation simply, enters the face-image after segmentation
Row feature identification, the problem that will cause identifying object mistake;(3) existing facial recognition techniques mistake
In simply, testing mechanism falls behind, and needs to improve to improve facial feature detection precision.
Accordingly, it would be desirable to a kind of new facial payment platform, it is possible in the case of overcoming above-mentioned deficiency,
Smoothly complete payment process based on facial characteristics identification, thus avoid client's economy to incur loss
Under premise, improve customer payment efficiency and speed.
Summary of the invention
In order to solve the problems referred to above, the invention provides a kind of supermarket face payment platform, first logical
After crossing facial recognition customer identification, use other customer identification authenticating device to carry out identity validation, keep away
The situation exempting from by mistake to pay occurs, secondly, when the client of queuing checkout is more, to each in image
The face-image of client is all split, and the client selecting actual checkout for cashier carries out follow-up
Facial characteristics identification, finally, also optimize facial recognition mechanisms, improve the precision of facial recognition,
Thus avoid loaded down with trivial details delivery operation, accelerate shopper checkout speed.
According to an aspect of the present invention, it is provided that a kind of supermarket face payment platform, described platform includes
Client's face detection system, payment system and control system, client's face detection system is worked as detection
The identity of the client of front checkout, control system connects with client's face detection system and payment system respectively
Connect, complete to prop up for controlling the identity of the client that payment system exports based on client's face detection system
Pay.
More specifically, in the face payment platform of described supermarket, including: iris receives equipment, is used for
Gather the iris information of client;Iris matching unit, receives equipment and the iris of far-end with iris respectively
Data base connects, and iris database has prestored everyone iris feature, receives based on iris
The iris information of equipment output finds the iris feature of coupling at iris database, and by the iris of coupling
Piece identity corresponding to feature is as confirming identity output;Frequency duplex communications equipment, for by frequency
Connection between division duplex communication link establishment characteristic matching equipment and the face recognition data storehouse of far-end,
Be additionally operable to by the iris database of frequency duplex communications link establishment iris matching unit and far-end it
Between connection;Static storage device, is used for having prestored preset reference face contour, pre-set image
Average, pre-set image variance and presetted pixel block size;CMOS visual sensing equipment, is arranged on receipts
Above silver platform, for shooting to obtain high definition crowd's image, high definition people to the crowd of queuing checkout
The resolution of group's image is 3840 × 2160;Face detection equipment, respectively with static storage device and
CMOS visual sensing equipment connects, and is used for receiving high definition crowd's image and preset reference face contour,
In high definition crowd's image, multiple face subimage is matched based on preset reference face contour;Display sets
Standby, be connected to receive with face detection equipment and show multiple facial subimage, display device also with
Touch screen, selects target face subimage with input based on cashier from multiple face subimages;
Mean filter equipment, is connected with display device and face detection equipment respectively, is used for receiving target face
Subimage also carries out mean filter process to target face subimage, to obtain corresponding mean filter figure
Picture;Histogram equalization equipment, is connected with mean filter equipment, is used for receiving mean filter image also
Mean filter image is carried out histogram equalization process, to obtain the intensity histogram of mean filter image
Figure;Illumination compensation equipment, is connected with static storage device and histogram equalization equipment respectively, is used for
Receive grey level histogram, pre-set image average and pre-set image variance, grey level histogram is carried out image
Revise so that the image average of image is equal to the figure of image after pre-set image average and correction after Xiu Zhenging
Image space difference is equal to pre-set image variance;Normalized equipment, respectively with static storage device and illumination
Compensation equipment connects, and image after being used for receiving presetted pixel block size and revising, after correction in image
Orient the position of right eye in face, point on the basis of right eye position, after revising, image marks off
There is the image to be identified of presetted pixel block size;Dct transform equipment, with normalized equipment even
Receive image to be identified, image to be identified is carried out dct transform and processes to obtain DCT image;
Vector extraction equipment, is connected with dct transform equipment to receive DCT image, left from DCT image
Upper angular zone extracts the low frequency component of preset number to constitute one-dimensional vector;Feature analysis equipment, with to
Amount extraction equipment connects to receive one-dimensional vector, one-dimensional vector carries out principal component analysis i.e. PCA to obtain
The PCA taking correspondence describes son, as the invariant features of image to be identified;Characteristic matching equipment, respectively
Being connected with the face recognition data storehouse of feature analysis equipment and far-end, face recognition data storehouse prestores
The PCA feature of everyone face-image, the PCA of feature based analytical equipment output describes
Son finds the PCA feature of coupling in face recognition data storehouse, and by corresponding for the PCA feature of coupling
Piece identity is as identifying identity output;DSP processes chip, respectively with display device, characteristic matching
Equipment, iris receive equipment and iris matching unit connects, when receiving knowledge at characteristic matching equipment
During other identity, the client to current checkout starts iris and receives equipment and iris matching unit to receive really
Recognizing identity, the client of current checkout is in the crowd of queuing checkout, when identifying identity and confirming identity
When being consistent, the value data one of identity and the cashier touch screen input by display device will be identified
Rise and be sent to payment devices to complete to pay, confirm to identifying that E-mail address corresponding to identity sends simultaneously
Mail, confirms that mail includes customer payment video;Payment devices, processes chip with DSP and is connected,
For receiving identity information and payment to complete to pay;Wherein, preset reference face contour is right
The figure that benchmark face-image carries out contours extract and obtains, pre-set image average is elected 140 as, is preset
Image variance elects 50 as, and presetted pixel block size elects 60 pixel × 65 pixels as.
More specifically, in the face payment platform of described supermarket: CMOS visual sensing equipment is additionally operable to
Record customer payment video.
More specifically, in the face payment platform of described supermarket: when DSP process chip is preset first
When not receiving identification identity after between, send identity validation failure signal.
More specifically, in the face payment platform of described supermarket: when DSP process chip is preset second
When not receiving confirmation identity after between, send identity validation failure signal.
More specifically, in the face payment platform of described supermarket: DSP process chip identify identity with
Confirm, when identity is inconsistent, to send identity validation failure signal.
More specifically, in the face payment platform of described supermarket: DSP process chip identify identity with
Confirm, when identity is consistent, to send identity validation pass signal.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram according to the supermarket face payment platform shown in embodiment of the present invention.
Fig. 2 is the frequency duplex communications according to the supermarket face payment platform shown in embodiment of the present invention
The block diagram of equipment.
Reference: 1 client's face detection system;2 payment systems;3 control systems;4 receive
Unit;5 transmitting elements;6 control units
Detailed description of the invention
Below with reference to accompanying drawings the embodiment of the supermarket face payment platform of the present invention is carried out in detail
Explanation.
Face is inherent as other biological characteristic (fingerprint, iris etc.) of human body, and he is only
One property and the superperformance being difficult to be replicated are the premise that identity differentiates to provide necessity, with other type
Bio-identification compare.
Facial recognition has a characteristic that non-imposed: user need not coordinate face collection to set specially
Standby, almost under unconscious state, just can obtain facial image, such sampling mode does not has
" mandatory ";Untouchable: user need not directly contact with equipment and just can obtain facial image;
Concurrency: the sorting of multiple face can be carried out under actual application scenarios, judge and identify;Except this
Outside, it also is compliant with visual characteristic: the characteristic of " knowing people with looks ", and simple to operate, visual result,
The features such as good concealment.
Along with technology develops, facial-recognition security systems is arranged in various payment system, and some companies are the most just
Transfer accounts platform researching and developing third party based on facial-recognition security systems.
Facial recognition pays and comprises the following steps: step one: during checkout, consumer only need to be at cashier
Photographic head on POS screen, system automatic camera, scanning consumer face, then image
Contrast with the storage information in data base;Step 2: consumer's facial information with paying is simultaneously
System is associated, and after waiting the identity information of consumer to show, he/her only need to touch on display screen
Clicking on " OK " to confirm, whole process of exchanges have i.e. been accused.
But, above-mentioned facial recognition pays and there is also certain drawback, such as, owing to face existence can
Variability, it is thus possible to exist identify mistake situation, and above-mentioned facial recognition pay validation testing
Simply simply pressing " OK " acknowledgement key, client cannot see whether that facial recognition has occurred that knowledge by mistake
Not, at this moment paying if carried out checkout, the account of other clients may incur loss;The most such as, exist
When the client of queuing checkout is more, facial recognition mode based on image detection may be by other clients'
Face-image is as identifying target;The most such as, the concrete facial characteristics identification that above-mentioned facial recognition pays
Pattern is excessively simple, is easily caused accuracy of identification the highest.
In order to overcome above-mentioned deficiency, the present invention has built a kind of supermarket face payment platform, fundamentally
Solve above-mentioned technical problem, it is possible to while improving the accuracy of facial recognition payment result, carry
The high efficiency paid, it is ensured that the account number safety of each client.
Fig. 1 is the block diagram according to the supermarket face payment platform shown in embodiment of the present invention,
Described platform includes that client's face detection system, payment system and control system, the detection of client's face are
System for detecting the identity of the client of current checkout, control system respectively with client's face detection system and
Payment system connects, for controlling the body of the client that payment system exports based on client's face detection system
Part completes to pay.
Then, continue the concrete structure of the supermarket face payment platform of the present invention is carried out further
Bright.
Described platform includes: iris receives equipment, for gathering the iris information of client;Iris mates
Equipment, the iris database receiving equipment and far-end respectively with iris is connected, and iris database is deposited in advance
Store up everyone iris feature, receive the iris information of equipment output in iris data based on iris
The iris feature of coupling is found in storehouse, and using piece identity corresponding for the iris feature of coupling as confirming body
Part output.
As in figure 2 it is shown, described platform includes: frequency duplex communications equipment, it is used for passing through FDD
Communication link sets up the connection between the face recognition data storehouse of characteristic matching equipment and far-end, is additionally operable to
By the company between frequency duplex communications link establishment iris matching unit and the iris database of far-end
Connect.Frequency duplex communications equipment includes receiving unit, transmitting element and control unit.Control unit is divided
It is not connected with reception unit, transmitting element.
Described platform includes: static storage device, be used for having prestored preset reference face contour,
Pre-set image average, pre-set image variance and presetted pixel block size.
Described platform includes: CMOS visual sensing equipment, is arranged on above cashier, for row
The crowd of team's checkout carries out shooting to obtain high definition crowd's image, and the resolution of high definition crowd's image is
3840×2160;Face detection equipment, respectively with static storage device and CMOS visual sensing equipment
Connect, be used for receiving high definition crowd's image and preset reference face contour, take turns based on preset reference face
Exterior feature matches multiple face subimage in high definition crowd's image.
Described platform includes: display device, is connected to receive with face detection equipment and shows multiple
Portion's subimage, display device is also with touch screen, with input based on cashier from multiple face subgraphs
Target face subimage is selected in Xiang;Mean filter equipment, sets with display device and face detection respectively
Standby connection, is used for receiving target face subimage and carrying out target face subimage at mean filter
Reason, to obtain corresponding mean filter image;Histogram equalization equipment, with mean filter equipment even
Connect, be used for receiving mean filter image and mean filter image being carried out histogram equalization process, with
Obtain the grey level histogram of mean filter image.
Described platform includes: illumination compensation equipment, respectively with static storage device and histogram equalization
Equipment connects, and is used for receiving grey level histogram, pre-set image average and pre-set image variance, to gray scale
Rectangular histogram carry out image correction so that after Xiu Zhenging the image average of image equal to pre-set image average and
After correction, the image variance of image is equal to pre-set image variance;Normalized equipment, respectively with static state
Storage device and illumination compensation equipment connect, image after being used for receiving presetted pixel block size and revising,
Orienting the position of right eye in face after correction in image, point on the basis of right eye position, from correction
Rear image marks off the image to be identified with presetted pixel block size.
Described platform includes: dct transform equipment, is connected to receive to be identified with normalized equipment
Image, carries out dct transform and processes to obtain DCT image image to be identified;Vector extraction equipment,
It is connected with dct transform equipment to receive DCT image, extracts from DCT image upper left corner area pre-
If the low frequency component of number is to constitute one-dimensional vector;Feature analysis equipment, is connected with vector extraction equipment
To receive one-dimensional vector, one-dimensional vector is carried out principal component analysis i.e. PCA to obtain corresponding PCA
Son is described, as the invariant features of image to be identified.
Described platform includes: characteristic matching equipment, and the face with feature analysis equipment and far-end is known respectively
Other data base connects, and the PCA that face recognition data storehouse has prestored everyone face-image is special
Levying, the PCA of feature based analytical equipment output describes son and finds coupling in face recognition data storehouse
PCA feature, and using piece identity corresponding for the PCA feature of coupling as identifying identity output.
Described platform includes: DSP processes chip, respectively with display device, characteristic matching equipment, rainbow
Film receives equipment and iris matching unit connects, when receiving identification identity at characteristic matching equipment
Time, the client to current checkout starts iris and receives equipment and iris matching unit to receive confirmation body
Part, the client of current checkout is in the crowd of queuing checkout, when identifying identity and confirming that identity is consistent
During conjunction, the value data one identifying identity and the cashier touch screen input by display device is risen
Deliver to payment devices to complete to pay, simultaneously confirm postal to identifying that E-mail address corresponding to identity sends
Part, confirms that mail includes customer payment video.
Described platform includes: payment devices, processes chip with DSP and is connected, is used for receiving identity information
With payment to complete to pay.
Wherein, preset reference face contour is that benchmark face-image is carried out the figure that contours extract obtains
Shape, pre-set image average elects 140 as, and pre-set image variance elects 50 as, and presetted pixel block size is elected as
60 pixel × 65 pixels.
Alternatively, in described platform: CMOS visual sensing equipment is additionally operable to record customer payment and regards
Frequently;When DSP process chip does not receives identification identity after the first Preset Time, send identity validation
Failure signal;When DSP process chip does not receives confirmation identity after the second Preset Time, send body
Part confirms failure signal;DSP processes chip in identification identity with when confirming that identity is inconsistent, sends
Identity validation failure signal;And DSP process chip is when identifying that identity is consistent with confirmation identity,
Send identity validation pass signal.
It addition, dsp chip, also referred to as digital signal processor, it is that one is particularly suitable for carrying out numeral
The microprocessor of signal processing computing, it is mainly applied is to realize real-time at various digital signal
Adjustment method.
According to the requirement of Digital Signal Processing, dsp chip typically has a following main feature: (1)
A multiplication and a sub-addition can be completed within an instruction cycle;(2) program and data space divides
Open, can simultaneously access instruction and data;(3) there is quick RAM in sheet, generally can be by solely
Vertical data/address bus accesses in two pieces simultaneously;(4) there is low overhead or without overhead loop and redirect
Hardware supported;(5) quickly interrupt processing and Hardware I/O support;(6) have in the monocycle
Multiple hardware address generators of interior operation;(7) can be with the multiple operation of executed in parallel;(8) support
Pile line operation, makes fetching, decodes and the operation such as execution can be with Overlapped Execution.
Use the supermarket face payment platform of the present invention, for prior art facial recognition payment devices not
Enough perfect technical problems, by payment devices being strengthened and carrying out perfect to paying link,
Improving the precision of facial recognition mechanisms itself, the introducing simultaneously assisting in identifying equipment helps facial recognition to prop up
Pay and avoid situation about by mistake paying to occur, thus while improving payment speed, it is ensured that the standard of payment
Really property.
Although it is understood that the present invention discloses as above with preferred embodiment, but above-mentioned enforcement
Example is not limited to the present invention.For any those of ordinary skill in the art, without departing from
Under technical solution of the present invention ambit, all may utilize the technology contents of the disclosure above to the technology of the present invention
Scheme makes many possible variations and modification, or is revised as the Equivalent embodiments of equivalent variations.Therefore,
Every content without departing from technical solution of the present invention, the technical spirit of the foundation present invention is to above example
Any simple modification, equivalent variations and the modification done, all still falls within technical solution of the present invention protection
In the range of.
Claims (7)
1. a using method for supermarket face payment platform, the method includes:
1) a kind of supermarket face payment platform is provided, described platform include client's face detection system,
Payment system and control system, client's face detection system is for detecting the body of the client of current checkout
Part, control system is connected with client's face detection system and payment system respectively, is used for controlling to pay system
The identity of system client based on the output of client's face detection system completes to pay;
2) this platform is used.
2. the method for claim 1, it is characterised in that described platform includes:
Iris receives equipment, for gathering the iris information of client;
Iris matching unit, the iris database receiving equipment and far-end respectively with iris is connected, iris
Data base has prestored everyone iris feature, receives the iris letter of equipment output based on iris
Cease the iris feature finding coupling at iris database, and by personage's body corresponding for the iris feature of coupling
Part is as confirming identity output;
Frequency duplex communications equipment, for by frequency duplex communications link establishment characteristic matching equipment with
Connection between the face recognition data storehouse of far-end, is additionally operable to by frequency duplex communications link establishment rainbow
Connection between film matching unit and the iris database of far-end;
Static storage device, be used for having prestored preset reference face contour, pre-set image average,
Pre-set image variance and presetted pixel block size;
CMOS visual sensing equipment, is arranged on above cashier, for entering the crowd of queuing checkout
Row shooting is to obtain high definition crowd's image, and the resolution of high definition crowd's image is 3840 × 2160;
Face detection equipment, is connected with static storage device and CMOS visual sensing equipment respectively, uses
In receiving high definition crowd's image and preset reference face contour, based on preset reference face contour in high definition
Crowd's image matches multiple face subimage;
Display device, is connected to receive with face detection equipment and shows multiple face subimage, display
Equipment also with touch screen, selects target face with input based on cashier from multiple face subimages
Portion's subimage;
Mean filter equipment, is connected with display device and face detection equipment respectively, is used for receiving target
Face subimage also carries out mean filter process to target face subimage, to obtain corresponding average filter
Ripple image;
Histogram equalization equipment, is connected with mean filter equipment, is used for receiving mean filter image also
Mean filter image is carried out histogram equalization process, to obtain the intensity histogram of mean filter image
Figure;
Illumination compensation equipment, is connected with static storage device and histogram equalization equipment respectively, is used for
Receive grey level histogram, pre-set image average and pre-set image variance, grey level histogram is carried out image
Revise so that the image average of image is equal to the figure of image after pre-set image average and correction after Xiu Zhenging
Image space difference is equal to pre-set image variance;
Normalized equipment, is connected with static storage device and illumination compensation equipment respectively, is used for connecing
Image after receiving presetted pixel block size and revising, orients the position of right eye in face after correction in image
Put, point on the basis of right eye position, after revising, image marks off and there is presetted pixel block size
Image to be identified;
Dct transform equipment, is connected to receive image to be identified, to be identified with normalized equipment
Image carries out dct transform and processes to obtain DCT image;
Vector extraction equipment, is connected with dct transform equipment to receive DCT image, schemes from DCT
As the low frequency component of preset number is extracted to constitute one-dimensional vector in upper left corner area;
Feature analysis equipment, is connected to receive one-dimensional vector with vector extraction equipment, enters one-dimensional vector
Row principal component analysis i.e. PCA describes son to obtain corresponding PCA, constant as image to be identified
Feature;
Characteristic matching equipment, is connected with the face recognition data storehouse of feature analysis equipment and far-end respectively,
Face recognition data storehouse has prestored the PCA feature of everyone face-image, and feature based divides
The PCA of desorption device output describes son and finds the PCA feature of coupling in face recognition data storehouse, and will
The piece identity that the PCA feature of coupling is corresponding exports as identification identity;
DSP processes chip, receives equipment and rainbow with display device, characteristic matching equipment, iris respectively
Film matching unit connects, when receiving identification identity at characteristic matching equipment, to current checkout
Client starts iris and receives equipment and iris matching unit to receive confirmation identity, the currently client of checkout
Be in the crowd of queuing checkout, when identify identity with confirm identity be consistent time, will identify identity with
The value data that cashier is inputted by the touch screen of display device is sent collectively to payment devices with complete
Become to pay, send to the E-mail address that identification identity is corresponding simultaneously and confirm mail, confirm that mail includes
Customer payment video;
Payment devices, processes chip with DSP and is connected, be used for receiving identity information and payment with complete
Become to pay;
Wherein, preset reference face contour is that benchmark face-image is carried out the figure that contours extract obtains
Shape, pre-set image average elects 140 as, and pre-set image variance elects 50 as, and presetted pixel block size is elected as
60 pixel × 65 pixels.
3. method as claimed in claim 2, it is characterised in that:
CMOS visual sensing equipment is additionally operable to record customer payment video.
4. method as claimed in claim 2, it is characterised in that:
When DSP process chip does not receives identification identity after the first Preset Time, send identity validation
Failure signal.
5. method as claimed in claim 2, it is characterised in that:
When DSP process chip does not receives confirmation identity after the second Preset Time, send identity validation
Failure signal.
6. method as claimed in claim 2, it is characterised in that:
DSP processes chip in identification identity with when confirming that identity is inconsistent, sends identity validation failure
Signal.
7. method as claimed in claim 2, it is characterised in that:
DSP processes chip in identification identity with when confirming that identity is consistent, and sends identity validation and successfully believes
Number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610204443.1A CN105894288A (en) | 2016-04-01 | 2016-04-01 | Using method of supermarket face payment platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610204443.1A CN105894288A (en) | 2016-04-01 | 2016-04-01 | Using method of supermarket face payment platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105894288A true CN105894288A (en) | 2016-08-24 |
Family
ID=57011996
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610204443.1A Withdrawn CN105894288A (en) | 2016-04-01 | 2016-04-01 | Using method of supermarket face payment platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105894288A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153955A (en) * | 2017-05-26 | 2017-09-12 | 苏衍杰 | A kind of commodity price method of payment and device |
CN109350094A (en) * | 2018-12-07 | 2019-02-19 | 余姚德诚科技咨询有限公司 | Ray image availability analysis institution |
CN109717961A (en) * | 2018-12-29 | 2019-05-07 | 宋明海 | Medical equipment mode analyzing platform |
TWI675573B (en) * | 2016-09-19 | 2019-10-21 | 香港商阿里巴巴集團服務有限公司 | Internet resource scheduling method and device, network red packet scheduling method |
-
2016
- 2016-04-01 CN CN201610204443.1A patent/CN105894288A/en not_active Withdrawn
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI675573B (en) * | 2016-09-19 | 2019-10-21 | 香港商阿里巴巴集團服務有限公司 | Internet resource scheduling method and device, network red packet scheduling method |
US11223571B2 (en) | 2016-09-19 | 2022-01-11 | Advanced New Technologies Co., Ltd. | Internet resource distributing method and device, and network red-envelope distributing method |
CN107153955A (en) * | 2017-05-26 | 2017-09-12 | 苏衍杰 | A kind of commodity price method of payment and device |
CN109350094A (en) * | 2018-12-07 | 2019-02-19 | 余姚德诚科技咨询有限公司 | Ray image availability analysis institution |
CN109717961A (en) * | 2018-12-29 | 2019-05-07 | 宋明海 | Medical equipment mode analyzing platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200175510A1 (en) | Method and system for facilitating facial-recognition-based payment system with multiple viewing angles and reduced mispayment risk | |
US10817705B2 (en) | Method, apparatus, and system for resource transfer | |
US20200334682A1 (en) | Face payment device, face payment method, face payment system, and machine-readable storage medium | |
CN105894288A (en) | Using method of supermarket face payment platform | |
CN105825384A (en) | Application method of face payment apparatus based on fingerprint auxiliary identify identification | |
US11521208B2 (en) | System and method for authenticating transactions from a mobile device | |
US20210166417A1 (en) | Image processing for occluded item recognition | |
US20210240998A1 (en) | Image processing for distinguishing individuals in groups | |
CN105894261A (en) | Usage method of cashier desk face payment system | |
US11113680B2 (en) | Self-service checkout counter checkout | |
CN111160202A (en) | AR equipment-based identity verification method, AR equipment-based identity verification device, AR equipment-based identity verification equipment and storage medium | |
CN105913264A (en) | Face payment device based on fingerprint auxiliary identity identification | |
CN105678290A (en) | Face payment platform based on image detection | |
US10223584B2 (en) | Document detection | |
CN109325333B (en) | Double-identification login and payment method and device | |
US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
WO2021166289A1 (en) | Data registration device, biometric authentication device, and recording medium | |
CN105894284A (en) | Supermarket face payment platform | |
US20220277311A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
CN105913263A (en) | Application method of face payment platform based on image detection | |
CN110415113A (en) | Finance data processing method, device, server and readable storage medium storing program for executing | |
US10218900B2 (en) | Document reorientation processing | |
CN108009921A (en) | Option trading systems based on computer vision and fingerprint recognition | |
CN112052706B (en) | Electronic device and face recognition method | |
US20230141541A1 (en) | Authentication control apparatus, authentication system, authentication control method, 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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160824 |