Utility model content
The problem that the utility model solves is to provide the Certificate of House Property printing terminal of a kind of identification self-aided terminal and correspondence, can carry out identification and the Certificate of House Property printing efficiently.
For solving the problem, the utility model provides a kind of identification self-aided terminal, comprising: I.D. recognition device, recognition of face treating apparatus, colour imagery shot, black and white camera; Described I.D. recognition device obtains ID (identity number) card information and the individual photo obtained on I.D., and described individual photo is sent to recognition of face treating apparatus; Described colour imagery shot and black and white camera is utilized to obtain face black white image and the coloured image of self-service terminal operation people respectively, black white image and coloured image are sent to recognition of face treating apparatus, and compare with individual photo respectively, obtain black white image diversity factor and coloured image diversity factor, when in described black white image diversity factor or coloured image diversity factor, any one is less than setting threshold value, assert that I.D. and self-aided terminal operator belong to same people.
Optionally, polaroid is provided with before described black and white camera.
Optionally, also comprise light filling unit, utilize light filling unit to carry out light filling to self-aided terminal operator.
Optionally, described light filling unit is infrared light compensating lamp.
Optionally, the infrared eyeglass before being arranged on black and white camera is also comprised.
Optionally, described infrared eyeglass and infrared light compensating lamp are the infrared eyeglass of phase co-wavelength and infrared light compensating lamp.
Optionally, described colour imagery shot and black and white camera are positioned on same level line, and the spacing between colour imagery shot and black and white camera is more than or equal to 5 centimetres.
Optionally, between described colour imagery shot and black and white camera, there is angle.
Optionally, also comprise display unit, for receiving and the image of display color camera, black and white camera acquisition.
The utility model embodiment also provides a kind of the Certificate of House Property printing terminal, comprise: there is described identification self-aided terminal, print control unit, the Certificate of House Property database, printer, when the identification signal that print control unit sends according to identification self-aided terminal, judge that I.D. and self-aided terminal operator belong to same people, print control unit sends call signal to the Certificate of House Property database, from the Certificate of House Property that the Certificate of House Property data base call is corresponding, and be sent to printer and print.
Compared with prior art, the technical program has the following advantages:
Made a video recording respectively by black and white camera and colour imagery shot, face black white image and face coloured image can be obtained respectively, with obtain separately compared with face coloured image, face black white image more easily identifies under high light, the individual photo of I.D. is compared with face black white image and face coloured image respectively, can more easily identify.
Embodiment
Below in conjunction with accompanying drawing, by specific embodiment, clear, complete description is carried out to the technical solution of the utility model.
Please refer to Fig. 1, be the structural representation of a kind of identification self-aided terminal of the utility model embodiment, comprise: I.D. recognition device 10, recognition of face treating apparatus 20, colour imagery shot 20, black and white camera 40; Described I.D. recognition device 10 obtains ID (identity number) card information and obtains the individual photo on I.D., and described individual photo is sent to recognition of face treating apparatus 20; Described colour imagery shot 20 and black and white camera 40 is utilized to obtain face black white image and the coloured image of self-service terminal operation people respectively, black white image and coloured image are sent to recognition of face treating apparatus 20, and compare with individual photo respectively, obtain black white image diversity factor and coloured image diversity factor, when in described black white image diversity factor or coloured image diversity factor, any one is less than setting threshold value, assert that I.D. and self-aided terminal operator belong to same people.
Described I.D. recognition device 10 is for identifying I.D. and reading identity card information.In the present embodiment, described I.D. recognition device 10 is the general sky identity card reader CP IDMR02/TG of Guangzhou Wan Te Information technology company limited.Described CP IDMR02/TG is a desk-top identity card reader aiming at country's distribution No.2 residence card and develop.This type adopts USB/RS232 alternative interface, it is integral type TYPE B contactless care read/write unit tool, include the radio frequency module for reading and writing of the special security module of Ministry of Public Security's Certification of Second Generation and Shanghai general sky independent development, by computer communication interface and installation ocr software in a computer, personal information and photograph are carried out showing and storing.In other embodiments, described I.D. recognition device can also be other suitable I.D. recognition devices.
In the present embodiment, described colour imagery shot 20 and black and white camera 30 are positioned on same level line, and the spacing between colour imagery shot 20 and black and white camera 30 is more than or equal to 5 centimetres, height and position and the Human Height of described colour imagery shot 20 and black and white camera 30 adapt.Because the spacing between described colour imagery shot 20 and black and white camera 30 is more than or equal to 5 centimetres, the position of face coloured image and the face black white image photographed is made to have deviation, when self-aided terminal operator does not stand in the dead ahead of identification self-aided terminal, have at least one can photograph complete facial image in two cameras and identify.
In other embodiments, between described colour imagery shot and black and white camera, there is angle, described colour imagery shot becomes divergent shape with the angle of black and white camera, make colour imagery shot and black and white camera can photograph larger scope, have at least one can photograph complete facial image in two cameras and identify.Simultaneously because colour imagery shot is different with the facial image angle that black and white camera photographs, both facial images of photographing can not be 100% identical, face black white image and face coloured image are compared, other people can be avoided to carry out spoofed identity identification self-aided terminal with the photo of litigant.
In the present embodiment, polaroid is provided with before described black and white camera.Due to compared with face coloured image, face black white image more easily identifies under high light, and individual photo that is easier and I.D. compares, and is provided with polaroid before black and white camera, is conducive to the facial image under acquisition high light and compares.
In the present embodiment, described identification self-aided terminal also comprises light filling unit, utilizes light filling unit to carry out light filling to self-aided terminal operator.Described light filling unit is infrared light compensating lamp or visible lamp etc.
In the present embodiment, described light filling unit is infrared light compensating lamp, and it is invisible light that infrared light compensating lamp produces infrared light, can not cause discomfort to self-aided terminal operator.
In other embodiments, infrared eyeglass can also be set before black and white camera, described infrared eyeglass can only through infrared light, the Infrared irradiation produced due to infrared light compensating lamp to face after can reflect, the infrared image of the clear acquisition face of black and white camera energy, simultaneously because the background around face can not the infrared light that produces of reflective infrared light compensating lamp, thus can clear acquisition facial image.
In other embodiments, described infrared eyeglass and infrared light compensating lamp are the infrared eyeglass of phase co-wavelength and infrared light compensating lamp, wavelength such as 830nm or 950nm etc., by selecting the corresponding wavelength infrared light that in natural light, content is less, background around face can not the infrared light that produces of reflective infrared light compensating lamp, thus can clear acquisition facial image.
In the present embodiment, identity card picture compares with face black white image, face coloured image after obtaining the face black white image of self-aided terminal operator, face coloured image and identity card picture by described recognition of face treating apparatus 20 respectively.
Described recognition of face treating apparatus 20 comprises four ingredients, is respectively: facial image detection, facial image pre-service, facial image feature extraction and matching and recognition.
Described facial image detection module is mainly used in the pre-service of recognition of face, and namely accurate calibration goes out position and the size of face in the picture.The pattern feature comprised in facial image is very abundant, as histogram feature, color characteristic, template characteristic, architectural feature and Haar feature etc.Face datection is exactly that this wherein useful information is picked out, and utilizes these features to realize Face datection.In the present embodiment, adopt Adaboost learning algorithm, Adaboost algorithm is a kind of method being used for classifying, and it is combined some more weak sorting techniques, combines the very strong sorting technique made new advances.Use Adaboost algorithm to pick out in Face datection process rectangular characteristic (Weak Classifier) that some can represent face, according to the mode of Nearest Neighbor with Weighted Voting, Weak Classifier is configured to a strong classifier, the cascade filtering of will the some strong classifiers obtained be trained to be composed in series a cascade structure again, improves the detection speed of sorter effectively.
Facial image pretreatment module is based on Face datection result, carries out process and finally serve feature extraction to image.The original image that system obtains, owing to being subject to restriction and the random disturbance of various condition, often directly can not using, must carry out the Image semantic classification such as gray correction, noise filtering at the commitment of image procossing to it.For facial image, its preprocessing process mainly comprises the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry correction, filtering and sharpening etc.
Facial image characteristic extracting module: the spendable feature of face identification system is divided into visual signature, pixels statistics feature, facial image conversion coefficient feature, facial image algebraic characteristic etc. usually.Face characteristic extracts and carries out for some feature of face.Face characteristic extracts, and also claim face to characterize, it is the process of face being carried out to feature modeling.The method that face characteristic extracts is summed up and is divided into two large 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 mainly obtains according to the shape description of human face and the range performance between them characteristic contributing to face classification, and its characteristic component generally includes Euclidean distance, curvature and angle etc. between unique point.Face is made up of the local such as eyes, nose, mouth, chin, and to these local and the geometric description of structural relation between them, can be used as the key character identifying face, these features are called as geometric properties.Knowledge based engineering face characterizes the method and template matching method that mainly comprise based on geometric properties.
Basic thought based on the method for algebraic characteristic is that the higher-dimension of face in spatial domain is described the low dimension formulation be converted in frequency domain or other spaces.Characterizing method based on algebraic characteristic is divided into linear projection characterizing method and non-linear projection characterizing method.Method based on linear projection mainly contains principal component analysis (PCA) or claims Karhunen-Loeve transformation, independent component analysis method and Fisher Fisher face.Nonlinear feature extraction method has two important branches: based on the Feature Extraction Technology of core and the Feature Extraction Technology of taking as the leading factor with manifold learning.
Matching and recognition module the characteristic of the facial image of extraction and the feature templates stored in database is carried out search mate, and by setting a threshold value, when similarity exceedes this threshold value, then exports mating the result obtained.Recognition of face is exactly face characteristic to be identified and the skin detection obtained are compared, and judges according to the identity information of similarity degree to face.This process is divided into again two classes: a class be confirm, be carry out one to one image ratio compared with process, another kind of be identification, be the process that one-to-many carries out images match contrast.
Black white image and coloured image are sent to recognition of face treating apparatus, and compare with individual photo respectively, obtain black white image diversity factor and coloured image diversity factor, when in described black white image diversity factor or coloured image diversity factor, any one is less than setting threshold value, assert that I.D. and self-aided terminal operator belong to same people.
In other embodiments, described recognition of face treating apparatus can also be existing recognition of face server, the recognition of face server etc. of the happy general electronics in such as Dongguan.
In other embodiments, described identification self-aided terminal also comprises display unit, for receiving and the image of display color camera, black and white camera acquisition.
Based on above-mentioned identification self-aided terminal, the utility model embodiment still provides a kind of the Certificate of House Property printing terminal, comprise: identification self-aided terminal 100, print control unit 200, printer 300, when the identification signal that print control unit 200 sends according to identification self-aided terminal 100, judge that I.D. and self-aided terminal operator belong to same people, print control unit 200 sends call signal to the Certificate of House Property database, from the Certificate of House Property that the Certificate of House Property data base call is corresponding, and be sent to printer 300 and print.
Described the Certificate of House Property database is the database in high in the clouds or the database of Land and Resources Bureau this locality, and when described the Certificate of House Property database is the database of Land and Resources Bureau this locality, described database also can be integrated in the Certificate of House Property printing terminal.
Although the utility model with preferred embodiment openly as above; but it is not for limiting the utility model; any those skilled in the art are not departing from spirit and scope of the present utility model; the Method and Technology content of above-mentioned announcement can be utilized to make possible variation and amendment to technical solutions of the utility model; therefore; every content not departing from technical solutions of the utility model; the any simple modification done above embodiment according to technical spirit of the present utility model, equivalent variations and modification, all belong to the protection domain of technical solutions of the utility model.