CN103488999A - Invoice data recording method - Google Patents

Invoice data recording method Download PDF

Info

Publication number
CN103488999A
CN103488999A CN201310413333.2A CN201310413333A CN103488999A CN 103488999 A CN103488999 A CN 103488999A CN 201310413333 A CN201310413333 A CN 201310413333A CN 103488999 A CN103488999 A CN 103488999A
Authority
CN
China
Prior art keywords
invoice
image information
recording method
data recording
character
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
Application number
CN201310413333.2A
Other languages
Chinese (zh)
Inventor
安俊峰
龚涛
卢萌萌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Donghua University
Original Assignee
Donghua University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Donghua University filed Critical Donghua University
Priority to CN201310413333.2A priority Critical patent/CN103488999A/en
Publication of CN103488999A publication Critical patent/CN103488999A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Character Input (AREA)

Abstract

The invention relates to an invoice data recording method which comprises the steps of obtaining invoice image information and inputting the invoice image information into a computer, and processing the invoice image information by means of the matlab software and storing data. The invoice data recording method is saving in cost, convenient and fast to use, and saving in time and labor.

Description

A kind of invoice data recording method
Technical field
The present invention relates to bill recording technique field, particularly relate to a kind of invoice data record and statistic of classification Forecasting Methodology.
Background technology
Invoice refers to all entity and individual in purchasing and selling commodities, utility service or accepts labor service, serves and be engaged in other business activities, the written document of the other side's that offers bank settlement, it is the legal voucher of financial revenue and expenditure, being the original foundation of accounting, is also the important evidence of auditing authority, tax authority's examination of law enforcement.All trades and professions are used right invoice now needs reimbursement, but carry out the typing operation for large-scale unit invoice bothers very much, needs the recording method of a kind of invoice data easily badly.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of invoice data recording method, cost-saving, convenient and swift, time saving and energy saving.
The technical solution adopted for the present invention to solve the technical problems is: a kind of invoice data recording method is provided, comprises the following steps:
(1) obtain the invoice image information, by the invoice image information collecting in computing machine;
(2) utilize matlab software to be processed the invoice image information, and the storage data.
Described step (2) comprises following sub-step:
(21) the invoice image information obtained is carried out to pre-service;
(22) adopt the mode of edge extracting to extract the invoice image information, and invoice is positioned;
(23) invoice behind location is carried out to Character segmentation and identification;
(24) content after identification is preserved.
Described step (23) comprises following sub-step:
(231) the invoice framing gathered is arrived to certain zone, the character image zone of invoice image information is cut apart;
(232) method that the application edge is cut apart is split the useful font on invoice, thus the single character in the separate text zone;
(233) by the method for matching identification Sample Storehouse, single character is identified.
Described step also comprises partial data is sued for peace after (2), notifies designated person's step when the result of summation is greater than preset value.
Also comprise the step of the data of storage being carried out to svm classification prediction after described step (2).
Beneficial effect
Owing to having adopted above-mentioned technical scheme, compared with prior art, have following advantage and good effect: the present invention is cost-saving in the present invention, convenient and swift, time saving and energy saving, can be applied to the unit that needs a large amount of uniform invoice information, there is good effect, alleviate staff's burden.
The accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is the process flow diagram of step in the present invention (2);
Fig. 3 is the process flow diagram of step in the present invention (23).
Embodiment
Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiment only are not used in and limit the scope of the invention for the present invention is described.Should be understood that in addition those skilled in the art can make various changes or modifications the present invention after the content of having read the present invention's instruction, these equivalent form of values fall within the application's appended claims limited range equally.
Embodiments of the present invention relate to a kind of invoice data recording method, as shown in Figure 1, comprise the following steps:
Step (1), obtain the invoice image information, by the invoice image information collecting in computing machine;
Step (2), utilize matlab software to be processed the invoice image information, and the storage data.Wherein, as shown in Figure 2, this step also comprises following sub-step:
(21) the invoice image information obtained is carried out to pre-service;
(22) adopt the mode of edge extracting to extract the invoice image information, and invoice is positioned;
(23) invoice behind location is carried out to Character segmentation and identification; Wherein, as shown in Figure 3, this step also comprises following sub-step:
(231) the invoice framing gathered is arrived to certain zone, facilitate the later stage extracted region Useful Information fixing to this, the character image zone of invoice image information is cut apart;
(232) the single character in the separate text zone: the method that the application edge is cut apart is split the useful font on invoice, detect the place that gray level or structure have sudden change, the termination that shows a zone is also the place that another zone starts.This uncontinuity is called edge, different gradation of image differences, and boundary generally has obvious edge, utilizes this feature can cut apart image.
(233) single character is identified: the main application technology of the identification of character is the matching identification Sample Storehouse, be about to all characters and set up Sample Storehouse, after extracting, realizes character the judgement of character by the comparison Sample Storehouse, can the intermediate result value such as confidence level will be produced in identifying, the reference frame that the personnel that give the invoice typing should be using discre value as input result as whether.
(24) content after identification is preserved.
Wherein, step can be sued for peace to partial data after (2), notifies the designated person when the result of summation is greater than preset value, can also carry out svm classification prediction to the data of storage.
Below take the invoice typing of colleges and universities and analytical work sets forth the present invention as example, is construed as, and is applied to other industry or has the operation of similar viewpoint to be considered as same invention.
At first invoice is manually added to some contents, take colleges and universities as example, on same a line of invoice face amount, add institute, such as information, material, humanity, etc., the use that also has invoice, such as data, scientific research, traffic etc., these words will be set in advance in the image processing and identification information bank the inside of matlab, for applying in the later stage identifying.Then with on video camera or computer with camera take invoice, and need to be by institute's information while taking, the information such as invoice use are all obtained, and the picture of shooting is saved as to picture format.Start the gui interface set under matlab, the image of storage is processed accordingly, comprise pre-service, edge extracting, invoice location, Character segmentation, character recognition, wherein character recognition comprises and correctly cuts apart the character image zone; The single word of correct separation; The single character of correct identification.Identified the face amount of invoice, institute, and use this moment.The content of the routine call identification by software and it is saved in the EXCEL or text document or .mat file of appointment.After having stored data, can according to institute, to the face amount of invoice, sue for peace with software, when the amount of certain institute has reached predetermined value, can utilize the means of communication case of matlab to be sent the processing operation of mail, will send warning to the mail of formulating realization and setting.Can also carry out sort operation to the use of invoice after having stored data, and can be with the prediction of classifying of the method for svm, and analyze accordingly which use and occupy corresponding how many ratios, the predetermined value of later formulation invoice is had to certain reference value.

Claims (5)

1. an invoice data recording method, is characterized in that, comprises the following steps:
(1) obtain the invoice image information, by the invoice image information collecting in computing machine;
(2) utilize matlab software to be processed the invoice image information, and the storage data.
2. invoice data recording method according to claim 1, is characterized in that, described step (2) comprises following sub-step:
(21) the invoice image information obtained is carried out to pre-service;
(22) adopt the mode of edge extracting to extract the invoice image information, and invoice is positioned;
(23) invoice behind location is carried out to Character segmentation and identification;
(24) content after identification is preserved.
3. invoice data recording method according to claim 2, is characterized in that, described step (23) comprises following sub-step:
(231) the invoice framing gathered is arrived to certain zone, the character image zone of invoice image information is cut apart;
(232) method that the application edge is cut apart is split the useful font on invoice, thus the single character in the separate text zone;
(233) by the method for matching identification Sample Storehouse, single character is identified.
4. invoice data recording method according to claim 1, is characterized in that, described step also comprises partial data is sued for peace after (2), notifies designated person's step when the result of summation is greater than preset value.
5. invoice data recording method according to claim 1, is characterized in that, also comprises the step of the data of storage being carried out to svm classification prediction after described step (2).
CN201310413333.2A 2013-09-11 2013-09-11 Invoice data recording method Pending CN103488999A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310413333.2A CN103488999A (en) 2013-09-11 2013-09-11 Invoice data recording method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310413333.2A CN103488999A (en) 2013-09-11 2013-09-11 Invoice data recording method

Publications (1)

Publication Number Publication Date
CN103488999A true CN103488999A (en) 2014-01-01

Family

ID=49829206

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310413333.2A Pending CN103488999A (en) 2013-09-11 2013-09-11 Invoice data recording method

Country Status (1)

Country Link
CN (1) CN103488999A (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105243365A (en) * 2015-09-28 2016-01-13 四川长虹电器股份有限公司 Data processing method and data processing system
CN105279525A (en) * 2015-11-19 2016-01-27 浪潮软件集团有限公司 Image processing method and device
CN105574522A (en) * 2014-11-06 2016-05-11 金蝶软件(中国)有限公司 Bill entry method and device
CN105630817A (en) * 2014-11-03 2016-06-01 航天信息股份有限公司 Electronic invoice content analysis method and system
CN105678612A (en) * 2015-12-30 2016-06-15 远光软件股份有限公司 Mobile terminal original certificate electronic intelligent filling system and method
CN105718928A (en) * 2016-01-20 2016-06-29 淄博职业学院 Accountant bill processing method
CN108446621A (en) * 2018-03-14 2018-08-24 平安科技(深圳)有限公司 Bank slip recognition method, server and computer readable storage medium
CN109426814A (en) * 2017-08-22 2019-03-05 顺丰科技有限公司 A kind of positioning of the specific plate of invoice picture, recognition methods, system, equipment
CN109492641A (en) * 2018-09-18 2019-03-19 上海延华智能科技(集团)股份有限公司 Energy bills input method and system, storage medium, server based on image recognition
CN110109907A (en) * 2017-12-27 2019-08-09 航天信息股份有限公司 A kind of storage of tax data, querying method and device
CN110188714A (en) * 2019-06-04 2019-08-30 言图科技有限公司 A kind of method, system and storage medium for realizing financial management under chat scenario
CN110648211A (en) * 2018-06-07 2020-01-03 埃森哲环球解决方案有限公司 Data validation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030031366A1 (en) * 2001-07-31 2003-02-13 Yulin Li Image processing method and apparatus using self-adaptive binarization
CN102831244A (en) * 2012-09-13 2012-12-19 重庆立鼎科技有限公司 Method for classified search of house property file image
CN202694374U (en) * 2012-05-15 2013-01-23 深圳长城开发科技股份有限公司 Portable device for invoice identification

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030031366A1 (en) * 2001-07-31 2003-02-13 Yulin Li Image processing method and apparatus using self-adaptive binarization
CN202694374U (en) * 2012-05-15 2013-01-23 深圳长城开发科技股份有限公司 Portable device for invoice identification
CN102831244A (en) * 2012-09-13 2012-12-19 重庆立鼎科技有限公司 Method for classified search of house property file image

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
代小红: "《基于机器视觉的数字图像处理与识别研究》", 31 March 2012, 西南交通大学出版社 *
何文基: "机动车销售统一***识别算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑2011年》 *
张闯 等: "基于字符边缘特征的手写账号切分算法", 《计算机工程》 *
迟国炜: "商业***手写数字识别***的设计与实现", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑2006年》 *

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105630817A (en) * 2014-11-03 2016-06-01 航天信息股份有限公司 Electronic invoice content analysis method and system
CN105630817B (en) * 2014-11-03 2019-06-25 航天信息股份有限公司 A kind of method and system of electronic invoice Context resolution
CN105574522A (en) * 2014-11-06 2016-05-11 金蝶软件(中国)有限公司 Bill entry method and device
CN105243365A (en) * 2015-09-28 2016-01-13 四川长虹电器股份有限公司 Data processing method and data processing system
CN105243365B (en) * 2015-09-28 2019-07-16 四川长虹电器股份有限公司 A kind of data processing method and data processing system
CN105279525B (en) * 2015-11-19 2018-11-27 浪潮金融信息技术有限公司 A kind of method and device of image procossing
CN105279525A (en) * 2015-11-19 2016-01-27 浪潮软件集团有限公司 Image processing method and device
CN105678612A (en) * 2015-12-30 2016-06-15 远光软件股份有限公司 Mobile terminal original certificate electronic intelligent filling system and method
CN105718928B (en) * 2016-01-20 2018-12-18 淄博职业学院 A kind of accounting bill processing method
CN105718928A (en) * 2016-01-20 2016-06-29 淄博职业学院 Accountant bill processing method
CN109426814A (en) * 2017-08-22 2019-03-05 顺丰科技有限公司 A kind of positioning of the specific plate of invoice picture, recognition methods, system, equipment
CN109426814B (en) * 2017-08-22 2023-02-24 顺丰科技有限公司 Method, system and equipment for positioning and identifying specific plate of invoice picture
CN110109907A (en) * 2017-12-27 2019-08-09 航天信息股份有限公司 A kind of storage of tax data, querying method and device
CN108446621A (en) * 2018-03-14 2018-08-24 平安科技(深圳)有限公司 Bank slip recognition method, server and computer readable storage medium
CN110648211A (en) * 2018-06-07 2020-01-03 埃森哲环球解决方案有限公司 Data validation
CN110648211B (en) * 2018-06-07 2023-10-03 埃森哲环球解决方案有限公司 data verification
CN109492641A (en) * 2018-09-18 2019-03-19 上海延华智能科技(集团)股份有限公司 Energy bills input method and system, storage medium, server based on image recognition
CN110188714A (en) * 2019-06-04 2019-08-30 言图科技有限公司 A kind of method, system and storage medium for realizing financial management under chat scenario

Similar Documents

Publication Publication Date Title
CN103488999A (en) Invoice data recording method
AU2017302250B2 (en) Optical character recognition in structured documents
US10140511B2 (en) Building classification and extraction models based on electronic forms
EP3430567B1 (en) Optical character recognition utilizing hashed templates
US20170206409A1 (en) Cognitive document reader
CN110909123B (en) Data extraction method and device, terminal equipment and storage medium
CN104123608A (en) Method and device for creating accounting records
CN110895696A (en) Image information extraction method and device
CN112434970A (en) Qualification data verification method and device based on intelligent data acquisition
US10200448B2 (en) Optimizing data exchange between client device and server
US20240212380A1 (en) Systems and methods for automatic context-based annotation
CN111462388A (en) Bill inspection method and device, terminal equipment and storage medium
CN104966109A (en) Medical laboratory report image classification method and apparatus
CN115171143A (en) Method and system for extracting full-face information of electronic invoice
CN111062262A (en) Invoice recognition method and invoice recognition device
WO2017069741A1 (en) Digitized document classification
CN111797922B (en) Text image classification method and device
Manjula et al. Identification and classification of multilingual document using maximized mutual information
CN113806368A (en) System and method for identifying document and automatically establishing database
CN112991037A (en) Credit certificate 46 domain analysis method and device
CN111046750A (en) Bill classification system and method
CN115688716A (en) Form processing method, device and equipment and readable storage medium
CN115034876A (en) Loan information auditing method and device based on OCR (optical character recognition) technology and computer equipment
CN113869857A (en) Shield machine production intelligent management system based on internet
CN117877016A (en) Video text extraction method, device, equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20140101

RJ01 Rejection of invention patent application after publication