CN202584267U - Ticket automatic identification system applying to mobile terminal - Google Patents
Ticket automatic identification system applying to mobile terminal Download PDFInfo
- Publication number
- CN202584267U CN202584267U CN2012202761874U CN201220276187U CN202584267U CN 202584267 U CN202584267 U CN 202584267U CN 2012202761874 U CN2012202761874 U CN 2012202761874U CN 201220276187 U CN201220276187 U CN 201220276187U CN 202584267 U CN202584267 U CN 202584267U
- Authority
- CN
- China
- Prior art keywords
- bill
- data
- processing module
- portable terminal
- ticket
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Character Discrimination (AREA)
Abstract
The utility model discloses a ticket automatic identification system applying to a mobile terminal. The ticket automatic identification system applying to the mobile terminal comprises a terminal processing module and a service processing module. The terminal processing module is arranged in the mobile terminal and used to identity and authenticate a ticket stored in the mobile terminal after being filmed, produces store ticket data which meet requirements through identification and authentication and stores the ticket data, then synchronizes the ticket data with the service processing module. The service processing module is arranged in a server and used to extract authority data and compare the authority data with the ticket data to judge whether the ticket data are identical with the authority data. The ticket automatic identification system applying to the mobile terminal can achieve automatic identification of the ticket, and has the advantages of being convenient to carry. In addition, the ticket automatic identification system applying to the mobile terminal can be integrated with other devices and carry out processing after identification.
Description
Technical field
The utility model belongs to the bill automatic identification field, especially relates to a kind of bill automatic recognition system that is applied to portable terminal.
Background technology
Though being arranged in the prior art, some equipment can realize the identification of bill; But owing to set the limitation of equipment and technology; Can't realize identification rapidly and efficiently; And existing identification equipment is because problem own, can't realize easy to carryly, also do not have the problems such as processing capacity after certain identification simultaneously.
In sum, the equipment of producing can realize bill identification automatically its can be easy to carry or be integrated in other equipment and can discern aftertreatment, just become the technical matters that needs to be resolved hurrily.
The utility model content
The utility model technical matters to be solved provides a kind of bill automatic recognition system that is applied to portable terminal, because problem own, can't realize easy to carryly to solve identification equipment, does not also have the problems such as processing capacity after certain identification simultaneously.
For solving the problems of the technologies described above, the utility model provides a kind of bill automatic recognition system that is applied to portable terminal, and this system comprises: terminal processing module and service processing module; Wherein
Said terminal processing module; Be arranged in the portable terminal; Be used for the bill that is stored in this portable terminal after taking is discerned and verification, produce satisfactory bill data and preservation, this bill data is preserved be synchronized to service processing module then through identification and verification;
Said service processing module is arranged in the server, is used to extract official's data, and high-ranking military officer's number formulary certificate checks with bill data, judges whether consistent with official data.
Further be: be arranged in the portable terminal; Be used for using the bill character repertoire that is provided with in OCR and this portable terminal to discern and verification to the bill that is stored in after taking in this portable terminal; Produce satisfactory bill data and preservation through identification and verification, this bill data is preserved be synchronized to service processing module then.
Further, wherein, said bill character repertoire comprises: the essential information of bill and characteristic information.
Further, wherein, said terminal processing module further is:
Be used for using OCR to carry out pre-service to the bill that is stored in after taking in this portable terminal; To carrying out printed page analysis through pretreated data; Cut apart going through the data after the printed page analysis; Through the bill character repertoire data of cutting apart through space are carried out Character segmentation; To carrying out feature extraction through the data after the Character segmentation; To carrying out classification processing through the data after the feature extraction; To carrying out aftertreatment through the data after the classification processing, produce satisfactory bill data and preservation, this bill data is preserved be synchronized to service processing module then.
In sum, compared with prior art, the described bill automatic recognition system that is applied to portable terminal of the utility model, can realize bill identification automatically its can be easy to carry or be integrated in other equipment and can discern aftertreatment.
Description of drawings
Fig. 1 is the utility model embodiment 1 described a kind of bill automatic identifying method FB(flow block) that is applied to portable terminal.
Fig. 2 is the idiographic flow block diagram of the identification described in the step 101 in the utility model embodiment 1 described method.
Fig. 3 is the utility model embodiment 2 described a kind of structured flowcharts that are applied to the bill automatic recognition system of portable terminal.
Embodiment
Below in conjunction with accompanying drawing the utility model is done further explain, but not as the qualification to the utility model.
As shown in Figure 1, be the utility model embodiment 1 described a kind of bill automatic identifying method that is applied to portable terminal, this method comprises the steps:
Wherein the identification described in the step 101 can be that the bill character repertoire is set in portable terminal; Some essential informations and the characteristic information of portable terminal through using OCR (Optical Character Recognition, optical character identification) technology to combine bill character repertoire decides bill itself to have.Such as when the lottery data, can the kind of information, issue information, temporal information, the notes that have in the lottery data be set at the bill character repertoire and count characteristics such as information or amount information, can also comprise some other characteristics:
1) background color of lottery ticket image all is more unified color;
2) image-region of the text filed and business card of lottery ticket generally separates;
3) the important text information in the lottery ticket, the stake content information is bigger than general text message font;
4) the main character in the lottery ticket is a Chinese and digital, and English character is less and be nonessential information;
5) composing of lottery ticket is generally from left to right horizontally-arranged.
In the bill character repertoire, can be provided with characteristic commonly used or field, carry out the distribution of weight, when discerning, can pay the utmost attention to and use characteristic or field commonly used earlier.
Being provided with in the algorithm of term weighing, first method is according to weights in oneself experience and the artificial tax of the domain knowledge of being grasped by expert or user.Simultaneously, the method for utilization statistics, the weight of just using the statistical information (like the same existing frequency between word frequency, the speech etc.) of text to come computational item, the weight calculation formula of employing is based on the TF of vector space model-IDF algorithm.After above-mentioned two results are compared, again difference is proofreaied and correct, thereby improve the precision of weight allocation.
Wherein the method for calibration described in the step 101 is automatic verification.Wherein, whether the verification meeting comes check results correct according to the logical relation that comprises in the recognition data automatically.For example: the kind of lottery ticket and playing method have determined to occur the numeral that some do not meet the playing method rule in the stake scheme, through such logic verify, just can further improve the correctness that automatic verification is judged, thereby improve whole discrimination.Utilize OCR that lottery information is carried out automatically and Intelligent Recognition.
Whether here step 103 is actually the data of announcing the winners in a lottery that said server extracts official to lottery data, and announcing the winners in a lottery data and lottery data mechanical check, grade, the amount of money of getting the winning number in a bond and getting the winning number in a bond with judges.Follow-up can also the operation as follows: said server is sent to portable terminal to judged result, and portable terminal is reminded after receiving judged result automatically.Said server also can be added up stake scheme and situation of Profit in the lottery data according to the algorithm that is provided with in advance simultaneously, and statistics is sent to portable terminal.The user just can bet through the lottery ticket choosing and selling scheme proposals that provides on the portable terminal like this.
As shown in Figure 2, the identifying described in the step 101 is specially and comprises in the above-described embodiments:
So-called pre-service is for denoising, strengthens Useful Information, and the degradation phenomena that input device for mobile terminal or other factors caused is restored.Usually, pre-service comprises that denoising (increasing the resolution of image), coloured image to original image transfer gray level image, slant correction, binaryzation to; Wherein:
Increase the resolution of image, exactly image carried out interpolation arithmetic, promptly through the value of original pixel in the image confirm the value of the pixel that will increase;
Two-value turns to the process that is treated to gray level image two-value (0,1), and the basic demand of binaryzation is: blank can not occur in (1) stroke; (2) stroke after the binaryzation keeps the characteristic of original language basically.
In order to obtain desirable bianry image, adopt the Threshold Segmentation technology, object and background are had strong contrast image cut apart effectively especially, its calculates zone simple and that can not overlap with the boundary definition of sealing, connection.Consider factors such as speed and actual effect, adopted the improved binarization method that whole Fujian value method Ostu algorithm and local Fujian value method Bernsen algorithm are combined among the utility model embodiment.The character image of bill is an integral body through what obtain after the binaryzation, comprising row with capable between, the blank of asking of word and word.
Slant correction is a prior art, is when obtaining image with image capture device, and specimen page is put upside down except placing, inclination that also might be slightly, and this situation also can influence identification.Inclination possibly be that the whole space of a whole page all has problems, and also possibly be local text block existing problems.When the angle of inclination is little, do not influence identifying, can ignore.If the pitch angle is excessive, just influenced the accuracy of identification.So also need carry out wing drop corrects.
So-called printed page analysis is to separate literal and image section, and it is that image is carried out aggregate analysis, identifies text fragment and image etc., just identify text filed, for ensuing work is prepared.
Said printed page analysis mainly is in order to distinguish textview field, image area and figure list area etc., and the purpose of doing like this is exactly in order to be partitioned into textview field.We have taked according to the characteristic on the lottery ticket of actual count, have taked pixel to investigate method, if large-area in some zones be foreground image, we will be regarded as non-text filed so.
It is that text image with through the data after the printed page analysis cuts into delegation of delegation that so-called row is cut apart, and the problem that mainly will solve is exactly that the situation of inclination appears in row.This step 1013 mainly is to improve accuracy of identification, avoids accuracy of identification not high.
So-called Character segmentation is mainly to be divided into for two steps, and the first step is that the character in the figure is extracted, is divided into independently little picture, and each little picture comprises and only comprise a character; Second step was that ready-portioned independent character picture is discerned.Because the character duration height of different fonts, font size is different, adds that up-down structure, left and right sides structure often appear in Chinese character, proposed very high requirement for the Character segmentation of Chinese and English, digital mixing.The method that we propose is to use template matches technology of the prior art, and the character types that pre-set bill paper corresponding region possibly occur are simplified the identification difficulty.Through the template matches technology, we can obtain the possible type of this bill figure through after the simple pre-service, know that promptly the character graphics that occurs in the specific region is Chinese, English or numeral, thus the accuracy that has greatly improved Character segmentation.
The statistical gradient histogram feature is adopted in said feature extraction, and concrete implementation is: 1) normalized image, obtain gradient image then; 2) gradient image is divided into a plurality of direction planes, each direction plane is divided into the cell of N*N; The quantity of 3) adding up gradient among each cell is as characteristic.
So-called feature extraction is the key component of bill identification, and the quality of feature extraction is the most critical key element of decision character identification rate height.This is the key of lottery ticket recognition system success or not, also is the focus of people's research in the area of pattern recognition.
Said classification processing is the mode identification method based on statistics, is specially the characteristic of calculating character to be identified and has trained the distance between the Character mother plate that obtains, confirms the result of identification according to the size of distance.Be convenient follow-up context Semantic Information Processing, a plurality of candidate's recognition results of the general output of character classification device.
The thought of classification processing is in feature space, to be classified as a certain classification to identifying object with statistical method, and the data image unification of different resolution is zoomed to certain size, is convenient to analyze contrast.The basic way of classification processing is to reach the loss minimum that error recognition rate is minimum or cause to being classified by the data after the feature extraction, its objective is according to the decision rule of formulating.
Said aftertreatment is for correcting some mistake of the data after the classification processing by contextual language message.To the cited embodiment of the utility model, implementation is two kinds: a kind of is to set up the lottery ticket dictionary; A kind of is to set up the lottery ticket language model.The corpus that the former needs is few relatively, and the latter then needs a large amount of language materials (lottery ticket content text).For a line of text, after the classification processing identification, each character picture all can obtain a plurality of candidate's recognition results.The recognition result of so whole line of text then has multiple combination; The aftertreatment here is to utilize dictionary or language model on the sorter base of recognition, the recognition result of whole line of text to be estimated, and obtains and estimates the recognition result of a best result as line of text.
Aftertreatment is in order to correct some wrong identifications, and this based on the syntax analysis, through in portable terminal, setting up the syntax rule storehouse, utilizes priori such as the meaning of a word, word frequency, semanteme to carry out the affirmation or the error correction of recognition result often.Such processing can further improve discrimination.
As shown in Figure 3, discern native system automatically for the utility model embodiment 2 described a kind of bills that are applied to portable terminal, this system comprises: terminal processing module 201 and service processing module 202; Wherein
Said terminal processing module 201; Be arranged in the portable terminal; Be used for the bill that is stored in this portable terminal after taking is discerned and verification, produce satisfactory bill data and preservation, this bill data is preserved be synchronized to service processing module 202 then through identification and verification;
Said service processing module 202 is arranged in the server, is used to extract official's data, and high-ranking military officer's number formulary certificate checks with bill data, judges whether consistent with official data.
Particularly, the concrete steps of the concrete operations mode of the system of this utility model and the method for aforesaid utility model are consistent, give unnecessary details no longer in detail here.
In sum; Compared with prior art; The described bill automatic identifying method that is applied to portable terminal of the utility model is through the optimization process of OCR (Optical Character Recognition, optical character identification) technology; With each item information in bill input be kept in the portable terminal, and be synchronized to server end and judge.The utility model can realize that once input of billing information, across a network, cross-terminal share; Do not receive the restriction of network type, terminal type, place and time, have very high movability and convenience.The utility model can be realized intelligentized self-adaptation to various bill pattern and format, is user-friendly to and runs and safeguard.
Certainly; The utility model also can have other various embodiments; Under the situation that does not deviate from the utility model spirit and essence thereof; Those of ordinary skill in the art can make various corresponding changes and distortion according to the utility model, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the utility model.
Claims (4)
1. a bill automatic recognition system that is applied to portable terminal is characterized in that this system comprises: terminal processing module and service processing module; Wherein
Said terminal processing module; Be arranged in the portable terminal; Be used for the bill that is stored in this portable terminal after taking is discerned and verification, produce satisfactory bill data and preservation, this bill data is preserved be synchronized to service processing module then through identification and verification;
Said service processing module is arranged in the server, is used to extract official's data, and high-ranking military officer's number formulary certificate checks with bill data, judges whether consistent with official data.
2. the bill automatic recognition system that is applied to portable terminal as claimed in claim 1 is characterized in that said terminal processing module further is:
Be arranged in the portable terminal; Be used for using the bill character repertoire that is provided with in OCR and this portable terminal to discern and verification to the bill that is stored in after taking in this portable terminal; Produce satisfactory bill data and preservation through identification and verification, this bill data is preserved be synchronized to service processing module then.
3. the bill automatic recognition system that is applied to portable terminal as claimed in claim 2 is characterized in that said bill character repertoire comprises: the essential information of bill and characteristic information.
4. the bill automatic recognition system that is applied to portable terminal as claimed in claim 3 is characterized in that said terminal processing module further is:
Be used for using OCR to carry out pre-service to the bill that is stored in after taking in this portable terminal; To carrying out printed page analysis through pretreated data; Cut apart going through the data after the printed page analysis; Through the bill character repertoire data of cutting apart through space are carried out Character segmentation; To carrying out feature extraction through the data after the Character segmentation; To carrying out classification processing through the data after the feature extraction; To carrying out aftertreatment through the data after the classification processing, produce satisfactory bill data and preservation, this bill data is preserved be synchronized to service processing module then.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012202761874U CN202584267U (en) | 2012-06-12 | 2012-06-12 | Ticket automatic identification system applying to mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012202761874U CN202584267U (en) | 2012-06-12 | 2012-06-12 | Ticket automatic identification system applying to mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN202584267U true CN202584267U (en) | 2012-12-05 |
Family
ID=47253656
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012202761874U Expired - Fee Related CN202584267U (en) | 2012-06-12 | 2012-06-12 | Ticket automatic identification system applying to mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN202584267U (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103995904A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Recognition system for image file electronic data |
CN104239872A (en) * | 2014-09-26 | 2014-12-24 | 南开大学 | Abnormal Chinese character identification method |
CN104916033A (en) * | 2015-05-28 | 2015-09-16 | 浪潮软件集团有限公司 | Bill information analysis method based on bank bill acceptance machine (CTM) |
CN105320951A (en) * | 2014-06-23 | 2016-02-10 | 株式会社日立信息通信工程 | Optical character recognition apparatus and optical character recognition method |
CN110659607A (en) * | 2019-09-23 | 2020-01-07 | 天津车之家数据信息技术有限公司 | Data checking method, device and system and computing equipment |
-
2012
- 2012-06-12 CN CN2012202761874U patent/CN202584267U/en not_active Expired - Fee Related
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103995904A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Recognition system for image file electronic data |
CN105320951A (en) * | 2014-06-23 | 2016-02-10 | 株式会社日立信息通信工程 | Optical character recognition apparatus and optical character recognition method |
CN105320951B (en) * | 2014-06-23 | 2018-11-20 | 株式会社日立信息通信工程 | Optical character recognition device and optical character recognition method |
CN104239872A (en) * | 2014-09-26 | 2014-12-24 | 南开大学 | Abnormal Chinese character identification method |
CN104916033A (en) * | 2015-05-28 | 2015-09-16 | 浪潮软件集团有限公司 | Bill information analysis method based on bank bill acceptance machine (CTM) |
CN110659607A (en) * | 2019-09-23 | 2020-01-07 | 天津车之家数据信息技术有限公司 | Data checking method, device and system and computing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102737242A (en) | Automatic bill recognition method and system applied to mobile terminal | |
CN202584267U (en) | Ticket automatic identification system applying to mobile terminal | |
CN102346847B (en) | License plate character recognizing method of support vector machine | |
CN108717543B (en) | Invoice identification method and device and computer storage medium | |
CN106156766A (en) | The generation method and device of line of text grader | |
CN103034848B (en) | A kind of recognition methods of form types | |
CN108255555B (en) | A kind of system language switching method and terminal device | |
CN110245573B (en) | Sign-in method and device based on face recognition and terminal equipment | |
CN106228675A (en) | The method and apparatus identifying true from false of bills | |
CN103177128A (en) | Method and system for processing bill crown word number information | |
CN103914680A (en) | Character image jet-printing, recognition and calibration system and method | |
CN110490238A (en) | A kind of image processing method, device and storage medium | |
CN109409377B (en) | Method and device for detecting characters in image | |
CN104217203A (en) | Complex background card face information identification method and system | |
CN103593642A (en) | Card-information acquisition method and system | |
CN105046553A (en) | Cloud intelligent invoice recognition inspection system and method based on mobile phone | |
Xia et al. | The study of license plate character segmentation algorithm based on vetical projection | |
CN109858420A (en) | A kind of bill processing system and processing method | |
CN110516664A (en) | Bill identification method and device, electronic equipment and storage medium | |
CN112766255A (en) | Optical character recognition method, device, equipment and storage medium | |
CN109447074A (en) | A kind of licence plate recognition method and terminal device | |
CN103488966A (en) | Intelligent mobile phone capable of identifying real-name ticket information | |
CN110765760A (en) | Legal case distribution method and device, storage medium and server | |
CN111062262B (en) | Invoice recognition method and invoice recognition device | |
CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121205 Termination date: 20140612 |