CN105893969A - Using method of automatic face recognition system - Google Patents
Using method of automatic face recognition system Download PDFInfo
- Publication number
- CN105893969A CN105893969A CN201610203811.0A CN201610203811A CN105893969A CN 105893969 A CN105893969 A CN 105893969A CN 201610203811 A CN201610203811 A CN 201610203811A CN 105893969 A CN105893969 A CN 105893969A
- Authority
- CN
- China
- Prior art keywords
- image
- equipment
- identity
- face
- subimage
- 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
- 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
-
- 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
- G06Q20/08—Payment architectures
- G06Q20/20—Point-of-sale [POS] network systems
- G06Q20/206—Point-of-sale [POS] network systems comprising security or operator identification provisions, e.g. password entry
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Accounting & Taxation (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to an automatic face recognition system comprising a GPRS communication device, a double-channel speaker, a master control device, and a face recognition device. The face recognition device and the GPRS communication device work collaboratively to confirm the identity of a customer based on an image of the customer. The master control device is connected with the GPRS communication device, the double-channel speaker and the face recognition device, and is used for determining a payment strategy based on the identity of the customer and making the double-channel speaker broadcast the customer identity confirmation result. With the system, a function of automatic payment is achieved based on the face information of customers.
Description
Technical field
The present invention relates to area of facial recognition, particularly relate to the use of a kind of automatization facial-recognition security systems
Method.
Background technology
The spendable feature of face identification system is generally divided into visual signature, pixels statistics feature, face
Image transform coefficients feature, facial image algebraic characteristic etc..Face characteristic extracts and is aiming at face
Some feature is carried out.Face characteristic extracts, and also referred to as face characterizes, and it is face to be carried out feature build
The process of mould.The method that face characteristic extracts is summed up and is divided into two big classes: one is Knowledge based engineering
Characterizing method;Another is the characterizing method based on algebraic characteristic or statistical learning.
Knowledge based engineering characterizing method is mainly according between the shape description of human face and they
Range performance obtain the characteristic contributing to face classification, its characteristic component generally includes feature
Euclidean distance, curvature and angle etc. between point.Face is by local structures such as eyes, nose, mouth, chins
Become, to these local and the geometric description of structural relation between them, can be as identifying the important of face
Feature, these features are referred to as geometric properties.Knowledge based engineering face characterizes and mainly includes based on geometry
The method of feature and template matching method.
Facial image coupling is as follows with the specific implementation identified: the characteristic number of the facial image of extraction
Scan for mating according to the feature templates of storage in data base, by setting a threshold value, when similar
Degree exceedes this threshold value, then result coupling obtained exports.Recognition of face is exactly by people to be identified
Face feature compares with the skin detection obtained, and believes the identity of face according to similarity degree
Breath judges.This process is divided into again two classes: a class is to confirm, is to carry out image one to one to compare
Process, another kind of is identification, is the one-to-many process that carries out images match contrast.
It is by face recognition application to payment platform that recognition of face pays, and is carried by customer face feature
Take, confirm customer identification, and the spending amount coordinating cashier to provide completes customer payment process.Whole
Individual payment process automaticity is high, and artificial interference link is few, for too much queuing checkout client
Time period, its effect is especially pronounced.
But, existing recognition of face payments mechanism there is also some problems: (1) identifies and pays ring
Save the most simple and crude, lack the secondary authentication mechanism of necessity;(2) too much queuing checkout client
Time, non-checkout client may be carried out facial recognition and payment;(3) recognition of face itself still has and changes
The space of kind performance.
Accordingly, it would be desirable to a kind of new facial recognition payment system, to existing recognition of face payments mechanism
Improve, increase assistant authentification means and client selects link, and the mode to facial features localization
It is optimized, thus while improving shopper checkout efficiency, fundamentally avoids the problem by mistake paid to go out
Existing.
Summary of the invention
In order to solve the problems referred to above, the invention provides a kind of automatization facial-recognition security systems, it is possible to increase
Add secondary identities authenticating device, after facial recognition identity, use secondary identities authenticating device to enter
The identity validation of one step, provides checkout client to select pattern for cashier, it is to avoid other client's quilts simultaneously
The situation of checkout occurs by mistake, pays it addition, also optimize existing facial recognition, it is ensured that face is known
Other accuracy, thus improve the integral working that facial recognition pays.
According to an aspect of the present invention, it is provided that a kind of automatization facial-recognition security systems, described system bag
Include GPRS communication equipment, two-way speaker, main control device and facial recognition device, facial recognition
Equipment and the collaborative operation of GPRS communication equipment, for confirming customer identification, master control based on custom image
Equipment is connected with GPRS communication equipment, two-way speaker and facial recognition device respectively, for base
Determine payment strategy in customer identification, the most also control two-way speaker and play customer identification confirmation knot
Really.
More specifically, in described automatization facial-recognition security systems, including: eye splitting equipment, point
It is not connected with SD storage device and Gaussian smoothing filter equipment to receive preset reference eye profile and treats
Identify image, in image to be identified, be partitioned into eye subimage based on preset reference eye profile;Volume
Head splitting equipment, is connected with eye splitting equipment and Gaussian smoothing filter equipment to receive eye respectively
Image and image to be identified, based on eye subimage position in image to be identified, by figure to be identified
In Xiang, image section more than eye subimage is split to obtain forehead subimage;Nose splitting equipment,
Be connected with SD storage device and Gaussian smoothing filter equipment respectively with receive preset reference nasal contours and
Image to be identified, is partitioned into nose image based on preset reference nasal contours in image to be identified;
Mouth splitting equipment, is connected with SD storage device and Gaussian smoothing filter equipment respectively and presets to receive
Benchmark mouth profile and image to be identified, split in image to be identified based on preset reference mouth profile
Go out mouth subimage;Chin splitting equipment, respectively with mouth splitting equipment and Gaussian smoothing filter equipment
Connect to receive mouth subimage and image to be identified, based on mouth subimage in image to be identified
Position, splits the image section below mouth subimage in image to be identified to obtain chin subgraph
Picture;Feature analysis equipment, respectively with eye splitting equipment, forehead splitting equipment, nose splitting equipment,
Mouth splitting equipment and chin splitting equipment connect, and determine in eye subimage that eye feature point is positioned at and treat
Identify that the coordinate in image, to export as eye coordinate, determines forehead characteristic point position in forehead subimage
Coordinate in image to be identified, to export as forehead coordinate, determines nose feature in nose image
The coordinate that point is positioned in image to be identified, to export as nose coordinate, determines mouth in mouth subimage
The coordinate that characteristic point is positioned in image to be identified, to export as mouth coordinate, determines in chin subimage
The coordinate that chin characteristic point is positioned in image to be identified is to export as chin coordinate;Characteristic matching sets
Standby, it is connected with the face recognition data storehouse of feature analysis equipment and far-end respectively, face recognition data storehouse
Prestore everyone each characteristic point of face-image coordinate in the face-image of place,
Feature based analytical equipment output eye coordinate, forehead coordinate, nose coordinate, mouth coordinate and under
Bar coordinate finds the face-image the highest with images match degree to be identified in face recognition data storehouse, and will
The piece identity that the face-image the highest with images match degree to be identified is corresponding exports as identification identity;
GPRS communication equipment, for setting up the face of characteristic matching equipment and far-end by GPRS communication link
Connection between portion's identification database, is also additionally operable to set up fingerprint matching by GPRS communication link and sets
Connection between the standby and fingerprint database of far-end;Two-way speaker, with MSP430 single-chip microcomputer even
Connect, for playing the voice message literary composition corresponding with identity validation failure signal or identity validation pass signal
Part;High-definition image collecting device, is arranged on above POS, for carrying out the crowd of queuing checkout
Shooting is to obtain high definition crowd's image, and high-definition image collecting device is additionally operable to record customer payment video;
Face detection equipment, is connected with SD storage device and high-definition image collecting device respectively, is used for receiving
High definition crowd's image and preset reference face contour, scheme high definition crowd based on preset reference face contour
Multiple face subimage is matched in Xiang;LCD display device, is connected to receive with face detection equipment
And showing multiple face subimage, LCD display device is also with touch screen, with based on cashier defeated
Enter from multiple face subimages select target face subimage, LCD display device be additionally operable to display with
Identity validation failure signal or text prompt information corresponding to identity validation pass signal;Geometric correction sets
Standby, it is connected with face detection equipment and LCD display device respectively, receives target face subimage also
Target face subimage carries out geometric correction process to obtain geometric correction image;Image rotation sets
Standby, it is connected with geometrical correction device to receive geometric correction image, geometric correction image is carried out image
Rotation processing rotates image to obtain;Image translation device, is connected with image orbiting facility to receive rotation
Turn image, carry out image translation process to obtain displacement images to rotating image;Image segmentation apparatus,
It is connected with SD storage device and image translation device respectively, is used for receiving pre-set image block size peace
Move image, displacement images is split the segmentation image obtaining pre-set image block size;Rectangular histogram
Equalization equipment, is connected with image segmentation apparatus, is used for receiving segmentation image and carrying out segmentation image
Histogram equalization processes, to obtain the grey level histogram of segmentation image;Gaussian smoothing filter equipment,
It is connected with histogram equalization equipment, is used for receiving grey level histogram and grey level histogram being carried out Gauss
The disposal of gentle filter, to obtain image to be identified;SD storage device, is used for having prestored and presets
Datum level contouring and pre-set image block size, be additionally operable to have prestored preset reference eye profile,
Preset reference nasal contours and preset reference mouth profile;Fingerprint receives equipment, for gathering client's
Finger print information;Fingerprint matching device, the fingerprint database receiving equipment and far-end respectively with fingerprint is connected,
Fingerprint database has prestored everyone fingerprint characteristic, receives the finger of equipment output based on fingerprint
Stricture of vagina information finds the fingerprint characteristic of coupling at fingerprint database, and by people corresponding for the fingerprint characteristic of coupling
Thing identity is as confirming identity output;MSP430 single-chip microcomputer, respectively with LCD display device, feature
Matching unit, fingerprint receive equipment and fingerprint matching device connects, when receiving at characteristic matching equipment
To when identifying identity, the client to current checkout starts fingerprint and receives equipment and fingerprint matching device to connect
Receiving and confirm identity, the client of current checkout is in the crowd of queuing checkout, when identifying identity and confirmation
When identity is consistent, identity and the cashier touch screen input by LCD display device will be identified
Value data is sent collectively to the payment devices of far-end to complete to pay, simultaneously to identifying that identity is corresponding
E-mail address sends and confirms mail, confirms that mail includes customer payment video;Wherein, preset reference
Face contour is that benchmark face-image carries out the figure that contours extract obtains, pre-set image block size
Elect 45 pixel × 50 pixels as;Preset reference eye profile carries for benchmark eyes image is carried out profile
The figure taken and obtain, preset reference nasal contours obtains for benchmark nose image is carried out contours extract
The figure obtained, preset reference mouth profile is that benchmark mouth image is carried out the figure that contours extract obtains
Shape;When MSP430 single-chip microcomputer does not receives identification identity after the first Preset Time, send identity true
Recognize failure signal, when MSP430 single-chip microcomputer does not receives confirmation identity after the second Preset Time, send out
Go out identity validation failure signal, MSP430 single-chip microcomputer identify identity with confirm identity inconsistent time,
Send identity validation failure signal, MSP430 single-chip microcomputer identify identity with confirmation identity be consistent time,
Send identity validation pass signal.
More specifically, in described automatization facial-recognition security systems: GPRS communication equipment is arranged on POS
On the housing of machine.
More specifically, in described automatization facial-recognition security systems: MSP430 single-chip microcomputer and feature
Arrange standby, fingerprint reception equipment and fingerprint matching device is integrated on one piece of surface-mounted integrated circuit.
More specifically, in described automatization facial-recognition security systems: surface-mounted integrated circuit is arranged on POS
In the control box of lower section.
More specifically, in described automatization facial-recognition security systems: use MSP430 single-chip microcomputer built-in
SD storage device replaced by memorizer.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the structure square frame according to the automatization's facial-recognition security systems shown in embodiment of the present invention
Figure.
Fig. 2 is that the high-definition image according to the automatization's facial-recognition security systems shown in embodiment of the present invention is adopted
The block diagram of collection equipment.
Reference: 1GPRS communication equipment;2 two-way speakers;3 main control devices;4
Portion identifies equipment;5 brightness detection unit;6 shooting unit;7 recording elements;8 control units
Detailed description of the invention
Below with reference to accompanying drawings the embodiment of automatization's facial-recognition security systems of the present invention is carried out in detail
Describe in detail bright.
Being directly to remit money owing to recognition of face pays, therefore, its security performance is particularly critical.Existing
Somebody's face identification pays and determines that face feature is i.e. remitted money after meeting, and does not accounts for face special
Levying the situation identifying mistake, meanwhile, the client of queuing checkout is a lot, it is easy to enter non-checkout client
Row facial characteristics identification, and, the existing recognition of face structural redundancy of mechanism own is high, also carries
High accuracy and the space of optimization function.
In order to overcome above-mentioned deficiency, the present invention has built a kind of automatization facial-recognition security systems, it is possible to solve
Certainly above-mentioned technical problem, is replacing loaded down with trivial details manual operation, while improving shopper checkout efficiency, from
Improve payments mechanism on the whole, it is ensured that the economic interests of each client.
Fig. 1 is the structure square frame according to the automatization's facial-recognition security systems shown in embodiment of the present invention
Figure, described system includes GPRS communication equipment, two-way speaker, main control device and facial recognition
The collaborative operation of equipment, facial recognition device and GPRS communication equipment, for confirming based on custom image
Customer identification, main control device sets with GPRS communication equipment, two-way speaker and facial recognition respectively
Standby connection, for determining payment strategy based on customer identification, the most also controls two-way speaker broadcasting
Customer identification confirms result.
Then, continue the concrete structure of automatization's facial-recognition security systems of the present invention is carried out further
Explanation.
Described system includes: eye splitting equipment, respectively with SD storage device and Gaussian smoothing filter
Equipment connects to receive preset reference eye profile and image to be identified, based on preset reference eye profile
Eye subimage it is partitioned in image to be identified;Forehead splitting equipment, respectively with eye splitting equipment
Connect to receive eye subimage and image to be identified with Gaussian smoothing filter equipment, based on eye subgraph
As the position in image to be identified, image section more than eye subimage in image to be identified is divided
Cut to obtain forehead subimage.
Described system includes: nose splitting equipment, respectively with SD storage device and Gaussian smoothing filter
Equipment connects to receive preset reference nasal contours and image to be identified, based on preset reference nasal contours
Nose image it is partitioned in image to be identified.
Described system includes: mouth splitting equipment, respectively with SD storage device and Gaussian smoothing filter
Equipment connects to receive preset reference mouth profile and image to be identified, based on preset reference mouth profile
Mouth subimage it is partitioned in image to be identified.
Described system includes: chin splitting equipment, respectively with mouth splitting equipment and Gaussian smoothing filter
Equipment connects to receive mouth subimage and image to be identified, based on mouth subimage at image to be identified
In position, by below mouth subimage in image to be identified image section split with obtain chin
Image.
Described system includes: feature analysis equipment, respectively with eye splitting equipment, forehead splitting equipment,
Nose splitting equipment, mouth splitting equipment and chin splitting equipment connect, and determine eye in eye subimage
The coordinate that portion's characteristic point is positioned in image to be identified, to export as eye coordinate, determines forehead subimage
The coordinate that middle forehead characteristic point is positioned in image to be identified, to export as forehead coordinate, determines nose
Coordinate during nose characteristic point is positioned at image to be identified in image, to export as nose coordinate, determines mouth
The coordinate that in portion's subimage, mouth feature point is positioned in image to be identified is to export as mouth coordinate, really
Fix the coordinate during chin characteristic point is positioned at image to be identified in bar subimage using defeated as chin coordinate
Go out.
Described system includes: characteristic matching equipment, and the face with feature analysis equipment and far-end is known respectively
Other data base connects, and face recognition data storehouse has prestored each spy of everyone face-image
Levy the coordinate a little in the face-image of place, the eye coordinate of feature based analytical equipment output, forehead
Coordinate, nose coordinate, mouth coordinate and chin coordinate are found and figure to be identified in face recognition data storehouse
As the face-image that matching degree is the highest, and by corresponding for the face-image the highest with images match degree to be identified
Piece identity as identify identity output.
Described system includes: GPRS communication equipment, for setting up feature by GPRS communication link
Connection between the face recognition data storehouse of matching unit and far-end, is also additionally operable to be communicated by GPRS
Connection between link establishment fingerprint matching device and the fingerprint database of far-end.
Described system includes: two-way speaker, is connected with MSP430 single-chip microcomputer, for play with
Identity validation failure signal or voice prompted file corresponding to identity validation pass signal.
As in figure 2 it is shown, described system includes: high-definition image collecting device, by brightness detection unit,
Shooting unit, recording elements and control unit composition, be arranged on above POS, for knot of queuing up
The crowd of account carries out shooting to obtain high definition crowd's image, and high-definition image collecting device is additionally operable to record and turns round and look at
Visitor pays video;Face detection equipment, connects with SD storage device and high-definition image collecting device respectively
Connect, be used for receiving high definition crowd's image and preset reference face contour, based on preset reference face contour
Multiple face subimage is matched in high definition crowd's image.
Described system includes: LCD display device, is connected to receive with face detection equipment and shows many
Individual face subimage, LCD display device is also with touch screen, with input based on cashier from multiple
Selecting target face subimage in face subimage, LCD display device is additionally operable to display and identity validation
Failure signal or text prompt information corresponding to identity validation pass signal.
Described system includes: geometrical correction device, shows with face detection equipment and LCD respectively and sets
Standby connection, receives target face subimage and target face subimage also carries out geometric correction process to obtain
Obtain geometric correction image;Image orbiting facility, is connected with geometrical correction device to receive geometric correction figure
Picture, carries out image rotation and processes to obtain rotation image geometric correction image;Image translation device,
It is connected with image orbiting facility and rotates image to receive, carry out image translation process to obtain to rotating image
Obtain displacement images.
Described system includes: image segmentation apparatus, respectively with SD storage device and image translation device
Connect, be used for receiving pre-set image block size and displacement images, split displacement images to obtain
The segmentation image of pre-set image block size;Histogram equalization equipment, is connected with image segmentation apparatus,
For receiving segmentation image and segmentation image being carried out histogram equalization process, to obtain segmentation image
Grey level histogram;Gaussian smoothing filter equipment, is connected with histogram equalization equipment, is used for receiving
Grey level histogram also carries out Gaussian smoothing filter process to grey level histogram, to obtain image to be identified.
Described system includes: SD storage device, be used for having prestored preset reference face contour and
Pre-set image block size, is additionally operable to prestore preset reference eye profile, preset reference nose wheel
Exterior feature and preset reference mouth profile;Fingerprint receives equipment, for gathering the finger print information of client;Fingerprint
Matching unit, the fingerprint database receiving equipment and far-end respectively with fingerprint is connected, and fingerprint database is pre-
First store everyone fingerprint characteristic, receive the finger print information of equipment output at fingerprint based on fingerprint
Data base finds the fingerprint characteristic of coupling, and using piece identity corresponding for the fingerprint characteristic of coupling as really
Recognize identity output.
Described system includes: MSP430 single-chip microcomputer, sets with LCD display device, characteristic matching respectively
Standby, fingerprint receives equipment and fingerprint matching device connects, when receiving identification at characteristic matching equipment
During identity, the client to current checkout starts fingerprint and receives equipment and fingerprint matching device to receive confirmation
Identity, the client of current checkout is in the crowd of queuing checkout, when identifying identity and confirming identity phase
When meeting, the amount of money number of identity and the cashier touch screen input by LCD display device will be identified
According to being sent collectively to the payment devices of far-end to complete to pay, simultaneously to the electronics postal identifying that identity is corresponding
Case sends and confirms mail, confirms that mail includes customer payment video.
Wherein, preset reference face contour is that benchmark face-image is carried out the figure that contours extract obtains
Shape, pre-set image block size elects 45 pixel × 50 pixels as;Preset reference eye profile is to benchmark
The figure that eyes image carries out contours extract and obtains, preset reference nasal contours is to benchmark nose figure
The figure obtained as carrying out contours extract, preset reference mouth profile is for carry out benchmark mouth image
Contours extract and the figure that obtains;MSP430 single-chip microcomputer does not receives identification after the first Preset Time
During identity, sending identity validation failure signal, MSP430 single-chip microcomputer does not connects after the second Preset Time
Receive confirmation identity time, send identity validation failure signal, MSP430 single-chip microcomputer identify identity with
Confirming, when identity is inconsistent, to send identity validation failure signal, MSP430 single-chip microcomputer is identifying body
Part, with when confirming that identity is consistent, sends identity validation pass signal.
Alternatively, in the system: GPRS communication equipment is arranged on the housing of POS;
MSP430 single-chip microcomputer receives equipment with characteristic matching equipment, fingerprint and fingerprint matching device is integrated in one
On block surface-mounted integrated circuit;Surface-mounted integrated circuit is arranged in the control box below POS;And can adopt
SD storage device is replaced with MSP430 single-chip microcomputer internal memory.
It addition, the abbreviation of general packet radio service technology (General Packet Radio Service),
He be gsm mobile telephone user can a kind of mobile data services.GPRS can say it is GSM
Continuity.GPRS, with the most different in the mode of channel transmission, is to come with package (Packet) formula
Transmission, the expense that therefore user is born is to calculate with its data transmission unit, and non-usage it is whole
Individual channel, the most inexpensively.The transfer rate of GPRS can be promoted to 56 even 114Kbps.
GPRS is often described as " 2.5G ", say, that this technology is positioned at the second filial generation (2G)
And between the third generation (3G) mobile communication technology.He is untapped by utilizing in GSM network
TDMA channel, it is provided that the data transmission of middling speed.GPRS breaches GSM net can only provide circuit
The mode of thinking of exchange, only by increasing corresponding functional entity and existing base station system being carried out portion
Dividing transformation to realize packet switch, the input of this transformation is the most little comparatively speaking, but the user obtained
Data rate is the most considerable.And, because the intermediary required for being no longer necessary to existing wireless application turns
Parallel operation, thus connect and transmission all can more convenient easily.So, user both can connect to the internet, ginseng
Add the interactive communications such as video conference, and the user of (VRN) on same video communication network, very
To can without passing through to dial up on the telephone, and continue connected to the network.
The communication mode of GPRS packet switch is in the communication mode of packet switch, and data are divided into one
The bag (packet) of measured length, (address mark therein indicates a packets headers before each bag
Where is mail in this packet).Data are not required to allocate in advance channel before transmitting, set up and connect.And
It is when each packet arrives, according to the information (such as destination address) in datagram header, temporarily
Find an available channel resource this datagram to be sent.In this load mode, data
Transmission and recipient's cochannel between the not fixing relation that takies, channel resource can be regarded as by
All of user shares and uses.A kind of burst is the most all shown due to data service
Property business characteristic, relatively big to the changes in demand of channel width, therefore use packet mode to carry out data
Transmission can better profit from channel resource.Such as one carries out the user that WWW browses, big portion
It is in browse state between timesharing, and the time really transmitted for data only accounts for very small scale.This feelings
According to the mode of fixing busy channel under condition, it will cause the bigger wasting of resources.
Use automatization's facial-recognition security systems of the present invention, pay system for prior art septum reset identification
System pays the technical problem that precision is the highest, first, face feature identification mechanism is carried out structure improvement,
Improve the reliability of facial characteristics identification itself, secondly, introduce fingerprinting mechanism and facial recognition is tied
Fruit is further confirmed, it addition, the client also adding cashier in certification link selected
Journey, thus go up in all fields and raising payment system precision is provided help.
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 (6)
1. a using method for automatization's facial-recognition security systems, the method includes:
1) a kind of automatization facial-recognition security systems is provided, described system include GPRS communication equipment,
Two-way speaker, main control device and facial recognition device, facial recognition device communicates with GPRS and sets
Standby collaborative operation, for confirming customer identification based on custom image, main control device leads to GPRS respectively
Letter equipment, two-way speaker and facial recognition device connect, for determining payment based on customer identification
Strategy, the most also controls two-way speaker and plays customer identification confirmation result;
2) this system is used.
2. the method for claim 1, it is characterised in that described system includes:
Eye splitting equipment, is connected with SD storage device and Gaussian smoothing filter equipment to receive respectively
Preset reference eye profile and image to be identified, based on preset reference eye profile in image to be identified
It is partitioned into eye subimage;
Forehead splitting equipment, is connected with eye splitting equipment and Gaussian smoothing filter equipment to receive respectively
Eye subimage and image to be identified, based on eye subimage position in image to be identified, will treat
In identification image, image section more than eye subimage is split to obtain forehead subimage;
Nose splitting equipment, is connected with SD storage device and Gaussian smoothing filter equipment to receive respectively
Preset reference nasal contours and image to be identified, based on preset reference nasal contours in image to be identified
It is partitioned into nose image;
Mouth splitting equipment, is connected with SD storage device and Gaussian smoothing filter equipment to receive respectively
Preset reference mouth profile and image to be identified, based on preset reference mouth profile in image to be identified
It is partitioned into mouth subimage;
Chin splitting equipment, is connected with mouth splitting equipment and Gaussian smoothing filter equipment to receive respectively
Mouth subimage and image to be identified, based on mouth subimage position in image to be identified, will treat
In identification image, the image section below mouth subimage is split to obtain chin subimage;
Feature analysis equipment, respectively with eye splitting equipment, forehead splitting equipment, nose splitting equipment,
Mouth splitting equipment and chin splitting equipment connect, and determine in eye subimage that eye feature point is positioned at and treat
Identify that the coordinate in image, to export as eye coordinate, determines forehead characteristic point position in forehead subimage
Coordinate in image to be identified, to export as forehead coordinate, determines nose feature in nose image
The coordinate that point is positioned in image to be identified, to export as nose coordinate, determines mouth in mouth subimage
The coordinate that characteristic point is positioned in image to be identified, to export as mouth coordinate, determines in chin subimage
The coordinate that chin characteristic point is positioned in image to be identified is to export as chin coordinate;
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 each characteristic point of everyone face-image in face, place
Coordinate in portion's image, the eye coordinate of feature based analytical equipment output, forehead coordinate, nose are sat
Mark, mouth coordinate and chin coordinate are found the highest with images match degree to be identified in face recognition data storehouse
Face-image, and piece identity corresponding for the face-image the highest with images match degree to be identified is made
For identifying identity output;
GPRS communication equipment, for setting up characteristic matching equipment and far-end by GPRS communication link
Face recognition data storehouse between connection, be also additionally operable to set up fingerprint by GPRS communication link
Arrange the connection between the standby and fingerprint database of far-end;
Two-way speaker, is connected with MSP430 single-chip microcomputer, unsuccessfully believes with identity validation for playing
Number or voice prompted file corresponding to identity validation pass signal;
High-definition image collecting device, is arranged on above POS, for carrying out the crowd of queuing checkout
Shooting is to obtain high definition crowd's image, and high-definition image collecting device is additionally operable to record customer payment video;
Face detection equipment, is connected with SD storage device and high-definition image collecting device respectively, is used for
Receive high definition crowd's image and preset reference face contour, based on preset reference face contour high definition people
Group's image matches multiple face subimage;
LCD display device, is connected to receive with face detection equipment and shows multiple face subimage,
LCD display device also with touch screen, selects from multiple face subimages with input based on cashier
Selecting target face subimage, LCD display device is additionally operable to display and identity validation failure signal or identity
Confirm the text prompt information that pass signal is corresponding;
Geometrical correction device, is connected with face detection equipment and LCD display device respectively, receives mesh
Mark face subimage also carries out geometric correction process to obtain geometric correction figure to target face subimage
Picture;
Image orbiting facility, is connected to receive geometric correction image, to geometry school with geometrical correction device
Positive image carries out image rotation and processes to obtain rotation image;
Image translation device, is connected with image orbiting facility and rotates image to receive, and enters rotating image
Row image translation processes to obtain displacement images;
Image segmentation apparatus, is connected with SD storage device and image translation device respectively, is used for receiving
Pre-set image block size and displacement images, split displacement images to obtain pre-set image block size
Segmentation image;
Histogram equalization equipment, is connected with image segmentation apparatus, is used for receiving segmentation image and to dividing
Cut image and carry out histogram equalization process, to obtain the grey level histogram of segmentation image;
Gaussian smoothing filter equipment, is connected with histogram equalization equipment, is used for receiving grey level histogram
And grey level histogram is carried out Gaussian smoothing filter process, to obtain image to be identified;
SD storage device, is used for having prestored preset reference face contour and pre-set image block size,
It is additionally operable to prestore preset reference eye profile, preset reference nasal contours and preset reference mouth
Profile;
Fingerprint receives equipment, for gathering the finger print information of client;
Fingerprint matching device, the fingerprint database receiving equipment and far-end respectively with fingerprint is connected, fingerprint
Data base has prestored everyone fingerprint characteristic, receives the fingerprint letter of equipment output based on fingerprint
Cease the fingerprint characteristic finding coupling at fingerprint database, and by personage's body corresponding for the fingerprint characteristic of coupling
Part is as confirming identity output;
MSP430 single-chip microcomputer, receives set with LCD display device, characteristic matching equipment, fingerprint respectively
Standby and fingerprint matching device connects, when receiving identification identity at characteristic matching equipment, to currently
The client of checkout starts fingerprint reception equipment and fingerprint matching device and confirms identity to receive, and currently settles accounts
Client be in the crowd of queuing checkout, when identify identity with confirm identity be consistent time, will identification
The value data that identity and cashier are inputted by the touch screen of LCD display device is sent collectively to far
The payment devices of end, to complete to pay, sends to the E-mail address that identification identity is corresponding simultaneously and confirms postal
Part, confirms that mail includes customer payment video;
Wherein, preset reference face contour is that benchmark face-image is carried out the figure that contours extract obtains
Shape, pre-set image block size elects 45 pixel × 50 pixels as;
Wherein, preset reference eye profile is that benchmark eyes image is carried out the figure that contours extract obtains
Shape, preset reference nasal contours is that benchmark nose image is carried out the figure that contours extract obtains, in advance
If benchmark mouth profile is that benchmark mouth image is carried out the figure that contours extract obtains;
Wherein, when MSP430 single-chip microcomputer does not receives identification identity after the first Preset Time, send
Identity validation failure signal, MSP430 single-chip microcomputer does not receives confirmation identity after the second Preset Time
Time, sending identity validation failure signal, MSP430 single-chip microcomputer is identifying identity and is confirming identity not phase
When meeting, sending identity validation failure signal, MSP430 single-chip microcomputer is identifying identity and is confirming identity
When being consistent, send identity validation pass signal.
3. method as claimed in claim 2, it is characterised in that:
GPRS communication equipment is arranged on the housing of POS.
4. method as claimed in claim 2, it is characterised in that:
MSP430 single-chip microcomputer receives equipment with characteristic matching equipment, fingerprint and fingerprint matching device is integrated
On one piece of surface-mounted integrated circuit.
5. method as claimed in claim 4, it is characterised in that:
Surface-mounted integrated circuit is arranged in the control box below POS.
6. the method as described in claim 2-5 is arbitrary, it is characterised in that:
MSP430 single-chip microcomputer internal memory is used to replace SD storage device.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610203811.0A CN105893969A (en) | 2016-04-01 | 2016-04-01 | Using method of automatic face recognition system |
CN201810181579.4A CN108304827A (en) | 2016-04-01 | 2016-04-01 | Automate facial-recognition security systems |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610203811.0A CN105893969A (en) | 2016-04-01 | 2016-04-01 | Using method of automatic face recognition system |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810181579.4A Division CN108304827A (en) | 2016-04-01 | 2016-04-01 | Automate facial-recognition security systems |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105893969A true CN105893969A (en) | 2016-08-24 |
Family
ID=57012275
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610203811.0A Pending CN105893969A (en) | 2016-04-01 | 2016-04-01 | Using method of automatic face recognition system |
CN201810181579.4A Withdrawn CN108304827A (en) | 2016-04-01 | 2016-04-01 | Automate facial-recognition security systems |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810181579.4A Withdrawn CN108304827A (en) | 2016-04-01 | 2016-04-01 | Automate facial-recognition security systems |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN105893969A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107231629A (en) * | 2016-08-31 | 2017-10-03 | 彭梅 | The account of mobile Internet application unbinds system for prompting and method with phone number |
CN108494941A (en) * | 2016-08-31 | 2018-09-04 | 陈玉兰 | A kind of phone system |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112150159B (en) * | 2020-05-22 | 2022-06-24 | 支付宝(杭州)信息技术有限公司 | Payment method, device and equipment based on face recognition |
US11921831B2 (en) | 2021-03-12 | 2024-03-05 | Intellivision Technologies Corp | Enrollment system with continuous learning and confirmation |
Citations (7)
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 |
US20100329568A1 (en) * | 2008-07-02 | 2010-12-30 | C-True Ltd. | Networked Face Recognition System |
CN102542299A (en) * | 2011-12-07 | 2012-07-04 | 惠州Tcl移动通信有限公司 | Face recognition method, device and mobile terminal capable of recognizing face |
US20120281874A1 (en) * | 2011-05-05 | 2012-11-08 | Lure Yuan-Ming F | Method, material, and apparatus to improve acquisition of human frontal face images using image template |
CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
CN204680060U (en) * | 2015-04-13 | 2015-09-30 | 济南舜软信息科技有限公司 | The identification of Network Based and biological characteristic and payment mechanism |
CN105095917A (en) * | 2015-08-31 | 2015-11-25 | 小米科技有限责任公司 | Image processing method, device and terminal |
-
2016
- 2016-04-01 CN CN201610203811.0A patent/CN105893969A/en active Pending
- 2016-04-01 CN CN201810181579.4A patent/CN108304827A/en not_active Withdrawn
Patent Citations (7)
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 |
US20100329568A1 (en) * | 2008-07-02 | 2010-12-30 | C-True Ltd. | Networked Face Recognition System |
US20120281874A1 (en) * | 2011-05-05 | 2012-11-08 | Lure Yuan-Ming F | Method, material, and apparatus to improve acquisition of human frontal face images using image template |
CN102542299A (en) * | 2011-12-07 | 2012-07-04 | 惠州Tcl移动通信有限公司 | Face recognition method, device and mobile terminal capable of recognizing face |
CN103198605A (en) * | 2013-03-11 | 2013-07-10 | 成都百威讯科技有限责任公司 | Indoor emergent abnormal event alarm system |
CN204680060U (en) * | 2015-04-13 | 2015-09-30 | 济南舜软信息科技有限公司 | The identification of Network Based and biological characteristic and payment mechanism |
CN105095917A (en) * | 2015-08-31 | 2015-11-25 | 小米科技有限责任公司 | Image processing method, device and terminal |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107231629A (en) * | 2016-08-31 | 2017-10-03 | 彭梅 | The account of mobile Internet application unbinds system for prompting and method with phone number |
CN107231629B (en) * | 2016-08-31 | 2018-02-06 | 上海净邻网络科技有限公司 | The account of mobile Internet application unbinds system for prompting and method with phone number |
CN108494941A (en) * | 2016-08-31 | 2018-09-04 | 陈玉兰 | A kind of phone system |
Also Published As
Publication number | Publication date |
---|---|
CN108304827A (en) | 2018-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107016127A (en) | A kind of electronics temporary identity authentication method and system based on biological identification technology | |
CN110502592B (en) | Project domain topic analysis system based on big data analysis technology | |
CN105893969A (en) | Using method of automatic face recognition system | |
CN104834839B (en) | A kind of code generating method, method for authenticating and associated terminal based on bar code | |
CN206684807U (en) | gate and gate system | |
CN103825744A (en) | Off-site personal digital certificate application method and system | |
US20220076268A1 (en) | Method and device for authenticating near-field information, electronic apparatus, and computer storage medium | |
CN106558115A (en) | Parking lot vehicles while passing control method and device | |
CN108510274A (en) | It is a kind of can visual identity image and Quick Response Code combine the method, apparatus of verification | |
CN110288755A (en) | The invoice method of inspection, server and storage medium based on text identification | |
CN107330992A (en) | Work attendance device and method, work attendance checking apparatus and method and computer-processing equipment | |
CN109754383A (en) | A kind of generation method and equipment of special efficacy video | |
CN108241999A (en) | A kind of generation method of invoice information, apparatus and system | |
CN105678290A (en) | Face payment platform based on image detection | |
CN105913241A (en) | Application method of customer authentication system based on image identification | |
CN105894262A (en) | Customer authentication system based on image identification | |
CN105894261A (en) | Usage method of cashier desk face payment system | |
CN105913264A (en) | Face payment device based on fingerprint auxiliary identity identification | |
CN109063682A (en) | A kind of method of Internet authentication authorization and data survey service | |
CN105913260A (en) | Automatic face identification system | |
CN112486977A (en) | Method and system for forging block by chain-linked mobile terminal | |
CN105913263A (en) | Application method of face payment platform based on image detection | |
CN105894287A (en) | Face payment platform based on iris-assisted identity authentication | |
CN105701705A (en) | System and method for replacing magnetic card with IC card on the basis of mobile Internet | |
US20150348033A1 (en) | Secure Payments Using Portable Communication Devices and Two Dimensional Codes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160824 |
|
WD01 | Invention patent application deemed withdrawn after publication |