CN1050102A - Check discriminating system - Google Patents
Check discriminating system Download PDFInfo
- Publication number
- CN1050102A CN1050102A CN 89102438 CN89102438A CN1050102A CN 1050102 A CN1050102 A CN 1050102A CN 89102438 CN89102438 CN 89102438 CN 89102438 A CN89102438 A CN 89102438A CN 1050102 A CN1050102 A CN 1050102A
- Authority
- CN
- China
- Prior art keywords
- signal
- image
- bus
- check
- address
- 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
- 238000003860 storage Methods 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims 1
- 230000014759 maintenance of location Effects 0.000 claims 1
- 238000003199 nucleic acid amplification method Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 19
- 230000008569 process Effects 0.000 abstract description 3
- 238000012546 transfer Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 12
- 238000001914 filtration Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 239000004744 fabric Substances 0.000 description 5
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 239000005338 frosted glass Substances 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008570 general process Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
What the present invention provided is a kind of recognition system---check discriminating system that is exclusively used in bank's identification check for transfer, cash on bank and is stamped the seal ticket.It is mainly by soft, hard two most of compositions, and software has systems such as the operation, user management, Flame Image Process of computing machine; Hardware has computing machine, cognitron to also have image input storage interface board (containing frame memory).It is easy to operate, check seal accurately, the time of checking is short, checks one piece of seal and only needs for 6 seconds, data volume is little, the total data volume of signature card is 1KB, its independent former computer operation.
Description
What the present invention relates to is a kind of recognition system-check discriminating system that is exclusively used in bank's identification check for transfer, cash on bank and is stamped the seal ticket.
Prior art is a universal image processing system as domestic TS-84 microcomputer image, graphic system.Main frame is IBM PC/XT, internal memory 576KB, 10M hard disk, 360K floppy disk * 2; Image subsystem is made up of picture frame memory, controller, image digitization device, display circuit and microcomputer image interface.Image, PaintShop comprise image enhancement, rim detection, image Segmentation, visual statistics, noise-removed filtering, geometric transformation, frequency domain processing, image operation and feature extraction, graphing capability etc.As abroad, image processing is used for remote sensing, remote measurement, medical diagnosis, fingerprint recognition, high energy physics, cell analysis, character (west literal, numeral) identification more.The general process of character recognition is: image input, visual histogram processing, noise-removed filtering, image binaryzation, geometric transformation, frequency domain are handled, pattern-recognition.Recognition system multipurpose small machine or medium-sized machine; Image input device is used flying-spot scanner, image dissector, facsimile recorder, TV camera, CCD gamma camera, graphic tablet always; Histogram is handled and is mainly contained equalization, regulationization; How noise-removed filtering judges filtering, binary map contraction, expansion etc. with averaging of multiple image, smoothing, medium filtering, noise; Binaryzation is commonly used decides thresholding by contrast with by measuring stroke width, and also useful P-quantile method, mode method, minimum error method are decided thresholding.It is that the conversion spatial domain is to frequency domain, a kind of technology of handling in frequency domain that frequency domain is handled.It is mainly used in image enhancement, recovery, encodes and describes, but its conversion, inverse transformation and operation time are long, under less demanding situation, does not promptly handle the too poor image of quality and generally need not.Pattern-recognition mainly is divided three classes, and a class is decision theory (statistics) method; Second class is sentence structure (structure) method; The 3rd class is a template matching method.The similarity criterion of first kind method has Discrimination Functions, minor increment, arest neighbors, maximum likelihood, minimum Bayes risk etc.; The criterion of second class has syntax parsing, error-correcting parsing, symbol string coupling, tree coupling, figure coupling, error correction figure coupling etc.; Technology such as Flexible formwork assembly commonly used, deformable model, rubber mask in the 3rd class methods.Yet they all can't be directly used in cashier's check identification.At present, user's check or other ticket received by bank, must from hundreds of even several thousand original signature cards, find out this user's signature card, seal with this seal and this user's check compares then, substantially to after last, again at the check Stamp Service, along the square chapter upper left corner to the lower right corner one folding, put on the corresponding position of original seal by broken line and further to check, this check is approved at the confirmation rear.These operations are promptly taken great energy again slowly, also require more skilled staff to operate simultaneously.
The purpose that the present invention proposes is to adapt to the modernization of current bank work, gets rid of original identification cashier's check, the method for collation of seal, makes a kind of check discriminating system that adopts modernization means.
The technical solution that the present invention provides, it mainly contains soft, hard two parts.Software section has operation system of computer, Subscriber Management System, image processing system; Hardware components has one in computing machine (main frame), and cognitron (mainly being made up of video camera and illumination, light adjusting circuit and colour filter, shading piece etc.) also has image input storage interface board (containing frame memory).
Accompanying drawing 1 is the work block diagram that the present invention provides.Also provided simultaneously connected mode of the present invention.
Accompanying drawing 2 is structural representations of cognitron.
In the accompanying drawing 1 15 is light sources, illumination is used, the 16th, photoelectric source, use for light source, the 17th, light adjusting circuit, form light adjusting system with light activated element, to guarantee that the luminous flux that enters camera lens keeps constant, the 18th, light activated element, effect sees 17, the 19th, gamma camera, take in image and be modulated into pal television signa and input to visual interface board, the 20th, amplifying circuit, the TV signal of amplifying gamma camera output is to satisfy the requirement of A/D chip input quantity, the 21st, monitor, monitor camera work (be not used in native system also can), the 22nd, separated in synchronization, separating TV Field and line synchronizing signal uses to control circuit, the 23rd, control circuit, produce control of control A/D chip operation signal and address and decoded signal, the 24th, the A/D chip, simulating signal is become the digital signal of 8bit, the 25th, frame is deposited, storage image digital signal and as a block RAM district of computing machine, the 26th, address control and decoding scheme, produce address control and address decode signal, the 27th, microcomputer image interface, generation reads or writes frame and deposits signal, perhaps do not read, do not write frame and deposit signal, the 28th, address bus, the address signal passage, the 29th, data bus, data signal channel, the 30th, main frame, (IBM PC/XT computing machine), the 31st, disk drive, the equipment of storage program and data, the 32nd, display, computer output equipment, the 33rd, printer, computer output equipment, the 34th, host bus, form by computer address bus and data bus and control bus, the 35th, image processing program, handle a series of programs of image, the 36th, system supervisor, the program of management image processing and banking, in the accompanying drawing 21 is support, support the shelf of gamma camera, be fixed on the base, the 2nd, case, shading and dustproof, the 19th, gamma camera, on effect is seen, the 4th, fixed mount, be used for fixing light source (bulb), the 5th, screw rod, with fastening frosted glass of nut and color filter plate, the 6th, nut, effect is with 5, the 7th, camera lens, the camera lens of using on the gamma camera, the 8th, shadow shield, shield outer light source, the 9th, color filter plate, make radiant spectrum blue (color filter plate is blue) partially, the 10th, frosted glass, light source is made a Fourier transformation, make irradiate light even in the part of machine mouth, the 11st, fixed cover, fixedly frosted glass is used, the 12nd, bulb, make light source, the 13rd, base, fixed support and worktable, the 14th, switch, battery main switch.
Provide the course of work below:
One, to the processing of original seal.
Seal on the signature card is placed on (cognitron is referring to accompanying drawing 2) under the cognitron machine mouth, after this seal corresponding account number of input, gamma camera in the cognitron is taken in its image, under programmed control, when picture intelligence finishes from the gamma camera field signal, the beginning input imagery is to interface board, and visual interface board separates the TV signal of the pal mode of input and handles, in the frame that the image (changing into digital signal by A/D converter) of absorption is deposited in interface board by the position of image with preface is deposited simultaneously; After frame was filled with, input channel was closed immediately.At this moment formed the character matrix of 256 * 256 * 8bit of the corresponding position of image of a width of cloth; After having imported a width of cloth, computing machine is called in internal memory with it; Receive a width of cloth again, and deposit the corresponding position addition of two width of cloth in calculator memory again; Altogether with eight width of cloth additions; Add keep after, computing machine carries out following processing: averaging of multiple image denoising, statistics with histogram, histogram equalization, histogram specification, smoothing, the edge strengthens, binaryzation, the rotation of image, the translation of image, noise-removed filtering, the condition code of getting Chinese character is denoising once more simultaneously, handles the disk that the back deposits result data in computing machine.
Two, the seal of check is handled:
Chapter that check is impressed is placed under the cognitron machine mouth: after the corresponding account number of input, the data that corresponding original seal is handled are called in the memory field of appointment earlier; By the gamma camera in the cognitron its image is taken in then; The process of the reception of being finished by visual interface board, storage one images is the same.Computing machine carries out following processing to this images matrix: visual statistics with histogram, and histogram equalization, histogram specification, smoothing, binaryzation, the rotation of image, the translation of image, noise-removed filtering, the condition code of getting Chinese character is denoising once more simultaneously; Data that obtain and the data that begin to call in are compared, see identical degree; If more than or equal to the number percent of regulation, just think that seal on this check and the seal of importing the account number correspondence conform to; Otherwise just think that seal covers fuzzyly or is not inconsistent.
Native system is easy to operate, check seal accurately, the time of checking is short, check one piece of seal generally only need 6 seconds (if host clock is higher than 4.77 million, then total time=6 second/its fast multiple of checking; If two pieces of seals lid is together, that is to say and depart from little and middle not far behindly up and down that handle two pieces of seals so simultaneously, host clock is 4.77 million, total processing time is about 9 seconds; And the operator still can continue to import following data during this period, and computer-internal can be write down these key entry values, so how many origin operation speed that do not slow down on the whole); Data volume is little, and the total data volume of signature card is 1KB, and 4,000 user's total volumies are 8,000,000～12,000,000 (the used seal of user is 2～3); Native system work is independent of the work of former computing machine, does not promptly influence the original operation of computing machine; Total system can be changed into very easily on 286,386 computing machines and use; Cheap, in the original computer system, increase more than 10,000 yuan and just can use native system, what performance was good also needs only more than 20,000 yuan; System architecture is simple; Easy to maintenance.
Native system software can use under DOS; Also can under the higher level lanquage that can call machine code, use, as DBASE II, BASIC etc.; Can also under the higher level lanquage that can carry out assembly language, carry out, as DBASE III, CDBASE III, FORTRAN77, C language, PASCAL(under UCSP supports) etc.
Native system is the holonomic system of handling at seal, and process software is that processing speed is fast with machine code (or assembly language) establishment.In addition, single handling procedure is more effective to some image processings, to other poor effect often then.The present invention does several programs together, and is all better to most image (except that image quality is too poor) treatment effects, as histogram is handled, edge enhancing, binaryzation program put together.Thresholding is set in the binaryzation has also used two kinds of methods; Use earlier minimum error method, then travels through whole picture matrix with suitable window, to minimum error method fixed two-value poor effect place reset thresholding with the mode method again; The and for example extraction of Hanzi features sign indicating number has integrated the method for sharpening and refinement.The present invention also can rotate at any angle to image.The method of general detection of straight lines is to remove to mate the image that will detect with numerous templates, and this will spend the considerable time; And the method for statistics edge variation number of times has been adopted in detection of the present invention, only just can detect with few time.
Claims (2)
1,, it is characterized in that its annexation by soft, hardware two most of check discriminating systems of forming; Gamma camera 19 in the cognitron is taken in image and is modulated pal television signa and inputs to visual interface board, TV signal is through amplifying circuit 20 amplifications and separate TV Field, line synchronizing signal through separated in synchronization 22, separated TV Field, line synchronizing signal are given control circuit 23, and the digital signal that control circuit 23 generation control A/D chips 24 working signals make A/D chip 24 become simulating signal 8bit is deposited in 25 by the frame that data bus 29 deposits interface board in; Control circuit 23 makes address control and decoding scheme 26 produce address control and address decode signal again, this signal deposits frame in by address bus 28 and deposits in 25, microcomputer image interface 27 is accepted the signal of address control and decoding scheme 26, generation reads or writes frame and deposits signal again, perhaps produce and do not read, do not write frame and deposit signal, by by computer bus, data bus, the host bus 34 that control bus is formed is given computing machine 30, calculate the external unit disk drive 31 of machine 30 again by the meter line, display 32, printer 33 storages, show, print, host bus 34 and 27 interfaces of microcomputer image are a data bus 29 and address bus 28.
2, check discriminating system according to claim 1 is characterized in that cognitron mainly is made up of gamma camera 19, photoelectric source 16, light adjusting circuit 17 and the color filter plate 9 used for illuminating light source 15, for light source, shadow shield 8 etc.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 89102438 CN1050102A (en) | 1989-08-25 | 1989-08-25 | Check discriminating system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 89102438 CN1050102A (en) | 1989-08-25 | 1989-08-25 | Check discriminating system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1050102A true CN1050102A (en) | 1991-03-20 |
Family
ID=4854712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 89102438 Pending CN1050102A (en) | 1989-08-25 | 1989-08-25 | Check discriminating system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1050102A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100390814C (en) * | 1999-03-01 | 2008-05-28 | 株式会社日立制作所 | Bill processing system and bill processing method |
| CN1781073B (en) * | 2003-05-02 | 2011-06-01 | 普驰信息技术有限公司 | Document processing method and system |
-
1989
- 1989-08-25 CN CN 89102438 patent/CN1050102A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100390814C (en) * | 1999-03-01 | 2008-05-28 | 株式会社日立制作所 | Bill processing system and bill processing method |
| CN1781073B (en) * | 2003-05-02 | 2011-06-01 | 普驰信息技术有限公司 | Document processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110309806B (en) | A gesture recognition system and method based on video image processing | |
| CN110309746A (en) | High-grade information security area list data information extracting method without communication interconnection | |
| CN105654072A (en) | Automatic character extraction and recognition system and method for low-resolution medical bill image | |
| CN101916364A (en) | Device and method for self-adaptive dial number recognition | |
| CN113076952B (en) | Text automatic recognition and enhancement method and device | |
| CN108416355A (en) | A kind of acquisition method of the industry spot creation data based on machine vision | |
| CN114332866B (en) | Literature curve separation and coordinate information extraction method based on image processing | |
| CN115273108A (en) | Artificial intelligence recognition automatic collection method and system | |
| GB2451437A (en) | Encoding content as a time varying two-dimensional pattern of luminosity modulations | |
| CN108304815B (en) | Data acquisition method, device, server and storage medium | |
| CN1050102A (en) | Check discriminating system | |
| CN116524503A (en) | Multi-line text line extraction method, device, equipment and readable storage medium | |
| CN105187686B (en) | A kind of Image Acquisition, identification and reading method and system based on CIS scannings | |
| US20210365675A1 (en) | Method, apparatus and device for identifying body representation information in image, and computer readable storage medium | |
| CN106557766B (en) | Fuzzy character processing method, system and electronic device | |
| CN106022246B (en) | A difference-based text extraction system and method for pattern background printed matter | |
| CN110348306A (en) | A kind of hand-written inputting method and system | |
| CN115546792A (en) | Data acquisition method and system based on image recognition | |
| CN119919943B (en) | Method and system for identifying and vertically extracting communication card number of ammeter | |
| CN116051864A (en) | An Intelligent Recognition System Based on Package Image | |
| CN119323796B (en) | Text detection and recognition method for medical bill image | |
| CN112001840A (en) | Energy consumption monitoring system, method and device based on Internet of things technology | |
| JP3378108B2 (en) | Binary image output device | |
| JPH10312381A (en) | Translation method and apparatus | |
| CN119323796A (en) | Text detection and recognition method for medical bill image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C01 | Deemed withdrawal of patent application (patent law 1993) | ||
| WD01 | Invention patent application deemed withdrawn after publication |