CN103617415A - Device and method for automatically identifying invoice - Google Patents
Device and method for automatically identifying invoice Download PDFInfo
- Publication number
- CN103617415A CN103617415A CN201310582905.XA CN201310582905A CN103617415A CN 103617415 A CN103617415 A CN 103617415A CN 201310582905 A CN201310582905 A CN 201310582905A CN 103617415 A CN103617415 A CN 103617415A
- Authority
- CN
- China
- Prior art keywords
- character
- invoice
- module
- error
- whole page
- 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
Images
Landscapes
- Character Input (AREA)
Abstract
The invention provides a method for automatically identifying an invoice. The method comprises the steps of (S1) obtaining an image formed by scanning the invoice to be identified in an optical mode, (S2) preprocessing the image, (S3) carrying out layout positioning on the preprocessed image, (S4) identifying characters in the layout positioning, and (S5) postprocessing and correcting the identified characters, thereby obtaining the invoice number. The invention further provides a device for automatically identifying the invoice. The device and method for automatically identifying the invoice resolve the difficulty of artificial search, improve efficiency, reduce the artificial error operation rate, can process businesses in batches, can be connected with an after-sales service platform system automatically, and realize automatic processing.
Description
Technical field
The present invention relates to image recognition technology.More specifically, the apparatus and method that relate to a kind of automatic identification invoice.
Background technology
In current after sale service, user applies for after sale service, and the record of selling goods need be inquired about according to user's invoice from after sale service plateform system by businessman, then determines whether to meet the regulation of the service of selling goods.And current, if search invoice, be all manually to search, then manually invoice number being input in operation system and inquiring about and examine, the method for operating of above-mentioned prior art has following shortcoming: manual operation, inefficiency; Invoice number comprises a lot of numeral, manually inputs misuse rate higher; Once can only input an invoice number, cannot batch processing invoice business.
Summary of the invention
For the shortcoming of above-mentioned prior art, the invention provides a kind of method of automatic identification invoice, comprising: a kind of method of automatic identification invoice, comprising: step S1), obtain invoice to be identified image after optical scanning; Step S2), described picture is carried out to pre-service;
Step S3), described pretreated image is carried out to space of a whole page location; Step S4), the character in space of a whole page location is carried out to character recognition; Step S5), the character identifying is proofreaded, thereby obtained invoice number.
Further, at step S1) in, adopt OCR technology to scan to obtain described image to invoice.
Further, at step S2) in, described pre-service comprises binaryzation, noise removal and slant correction.
Further, at step S3) in, comprising: 1) according to invoice type, set space of a whole page identified region; 2) to this regional assignment two-dimensional coordinate; 3) character in this region is identified.
Further, described step S5) comprising: according to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is concentrated the logicality of the character of this error character and front and back to find out the most logical character from character data, replace described error character.
Further, described step S5) comprising: according to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is replaced described error character by the most similar character of font in described character database.
The present invention also provides a kind of device of automatic identification invoice, comprising: image collection module, and described image collection module is for obtaining invoice to be identified image after optical scanning; Pretreatment module, described pretreatment module is for carrying out pre-service to described picture; Space of a whole page locating module, described space of a whole page locating module is for carrying out space of a whole page location to described pretreated image; Identification module, described identification module is for carrying out character recognition to the character of space of a whole page location; Checking module, described checking module is for the character identifying is carried out to aftertreatment and check and correction, thus acquisition invoice number.
Further, described image collection module comprises the scan module that adopts OCR technology to scan invoice.
Further, described pretreatment module is configured to described image to carry out binaryzation, noise removal and slant correction.
Further, described space of a whole page identification module is configured to: 1) according to invoice type, set space of a whole page identified region; 2) to this regional assignment two-dimensional coordinate; 3) character in this region is identified.
Further, described checking module is configured to: according to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is concentrated the logicality of the character of this error character and front and back to find out the most logical character from character data, replace described error character.
Further, described checking module is configured to: according to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is replaced described error character by the most similar character of font in described character database.
The invention solves the difficulty of manually searching, improved efficiency; And the present invention has reduced artificial incorrect operation rate; And the present invention can also batch processing business, automatic butt after sale service plateform system, realizes robotization and processes.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of method of the present invention;
Fig. 2 is the structural representation of device of the present invention.
Embodiment
Fig. 1 has shown the process flow diagram of method of the present invention.
First, in step S1, invoice to be identified is carried out to optical scanning, obtain image.To the scanning of invoice, can adopt OCR technology (Optical Character Recognition, optical character identification), OCR technology is utilized the character of printing on photoelectric technology scanning paper, by detecting its shape of dark, bright mode decision, then with character identifying method, shape is translated into the accessible word of computing machine.How debug or utilize supplementary to improve recognition correct rate is the most important problem of OCR.
The form of the described image obtaining can be various, if scan rate setting is very high, can also compress preservation to described image.
At step S2, described picture is carried out to pre-service.Pre-service mainly comprises binaryzation (for example colour picture, need to carry out color processing, and being defined foreground information is black, and background is white, is conducive to like this identification of unified follow-up invoice number character), and noise is removed, slant correction etc.
At step S3, described pretreated image is carried out to space of a whole page location.
Space of a whole page location is determined by space of a whole page coordinate, when invoice is identified, only identifies the rectangular area that space of a whole page coordinate is demarcated, and so just, without other information of being concerned about picture, has reduced data processing amount.Meanwhile, because invoice is all that machine is printed, therefore there is not Character segmentation problem (Characters Stuck, disconnected pen).
In a preferred embodiment, difference due to the invoice space of a whole page, utilize invoice template parameter to carry out space of a whole page location, template parameter comprises: space of a whole page coordinate, resolution, invoice kind (common invoice, VAT invoice etc.), scanner models (different invoice scanners is for the invoice of the different spaces of a whole page) etc.Further, (the numbering rule of correspondence is generally: numbering-invoice type-resolution-scanner models), directly extract next time like this invoice template parameter having set can be saved as to template numbering.In this preferred embodiment, first by reading the invoice picture coordinate information in template parameter acquisition of information template parameter, then locate the rectangular area that this coordinate forms.
At step S4, the character behind space of a whole page location is carried out to character recognition.
Identification to the character in the rectangular area behind space of a whole page location has been identified by the character recognition module of apparatus of the present invention.For invoice number rectangular area, it is set to a two-dimensional array, because picture is all the face consisting of point, and the pre-service of previously having carried out has been black by the foreground information of picture, background is white, the position that so just can distinguish black is real point, the position of white is imaginary point, and the actual two-dimensional array finally obtaining, is exactly string number, and this numeral is preserved, facilitate follow-up reading.
Preferably, at step S5, the character identifying is proofreaded, thereby obtained invoice number.Obtain after invoice number, can this invoice of unique identification.Check and correction is that the invoice number character identifying is carried out to logic corrigendum.
Check and correction comprises identification error character, and for example, the character occurring in invoice number belongs to a complete character storehouse, and the character of identification not in this character repertoire time, shows that this is an error character.Check and correction also comprises corrigendum character, identifies after error character, according to the character before and after this error character, from described character repertoire, search the most logically, replace described error character, or, from character repertoire, search the most similar character of font, replace described error character.
Preferably, above-mentioned check and correction process can be stored in check and correction daily record, check and correction daily record comprises: error character, correct character, template numbering, correct frequency, forms similar candidate characters collection, according to the discriminating digit character of front and back, from character data, concentrate and to find out the most logically, proofread accordingly.
Obtain after invoice number, get final product batch processing invoice to docking corresponding after sale service plateform system, automatically process invoice information after sale.Multi-threaded parallel reads the invoice number in internal memory, carry out batch processing, according to InvoiceCode(invoice number) the unique identification InvoiceId (invoice ID) of data, in service platform system, searching reference numeral afsServiceId(after sale service odd numbers with it after sale) after sale service list, and after sale service list is applied for processing according to customer order (order number OrderId), to this, can judge the after sale service forms data of this application, whether meet this condition of invoice after sale of processing.
The present invention has improved invoice business operation person work efficiency, for client brings faster and better after sale service, provides strong support.The unit cost ，Wei company that has reduced corporate business production brings income.Batch processing invoice business of the present invention, docking after sale service, realizes the robotization of business processing.Applicant has carried out close beta to the present invention, in one month in application in the inventive method, the automatic identification amount of artificial input quantity and the inventive method is contrasted, and invoice reject rate, misclassification rate have reduced by 10%, recognition speed has improved 30%.
According to a second aspect of the invention, the present invention also proposes a kind of device of automatic identification invoice, as shown in Figure 2.The device of described automatic identification invoice comprises image collection module, and this Image Acquisition piece comprises one scan module, and this scan module carries out optical scanning to invoice to be identified, obtains image.This image collection module adopts OCR technology (Optical Character Recognition, optical character identification) to scan.Preferably, image collection module also has image compression module, for when scan rate setting is very high, described image is compressed to preservation.
In one embodiment, described image collection module can not comprise scan module, but from the external world, obtain the image of invoice after OCR scanning, for example this image collection module is connected to one scan instrument, this scanner is image by invoice scanning, and this image collection module is obtained the image of invoice after OCR scanning from this scanner.
The device of described automatic identification invoice also comprises pretreatment module.The image that described pretreatment module obtains described scan module carries out pre-service.Pre-service mainly comprises binaryzation (for example colour picture, need to carry out color processing, and being defined foreground information is black, and background is white, is conducive to like this identification of unified follow-up invoice number character), and noise is removed, slant correction etc.
The device of described automatic identification invoice also comprises space of a whole page locating module.Described space of a whole page locating module carries out space of a whole page location to described pretreated image.
The device of described automatic identification invoice also comprises identification module.Described identification module carries out character recognition to the character in space of a whole page location.
The device of described automatic identification invoice also comprises checking module.Described checking module carries out aftertreatment and check and correction to the character identifying.
The device that has had automatic identification invoice of the present invention, can dock this device with existing after sale service plateform system, the invoice number identifying is input in after sale service plateform system, carries out invoice inquiry, has removed the trouble of artificial input from.But also can carry out batch processing input, improved work efficiency.
Claims (12)
1. automatically identify a method for invoice, it is characterized in that, comprising:
Step S1), obtain invoice to be identified image after optical scanning;
Step S2), described picture is carried out to pre-service;
Step S3), described pretreated image is carried out to space of a whole page location;
Step S4), the character in space of a whole page location is carried out to character recognition;
Step S5), the character identifying is proofreaded, thereby obtained invoice number.
2. the method for automatic identification invoice according to claim 1, is characterized in that, at step S1) in, adopt OCR technology to scan to obtain described image to invoice.
3. the method for automatic identification invoice according to claim 1, is characterized in that, at step S2) in, described pre-service comprises binaryzation, noise removal and slant correction.
4. the method for automatic identification invoice according to claim 1, is characterized in that, at step S3) in, comprising:
1) according to invoice type, set space of a whole page identified region;
2) to this regional assignment two-dimensional coordinate;
3) character in this region is identified.
5. the method for automatic identification invoice according to claim 1, is characterized in that, described step S5) comprising:
According to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is concentrated the logicality of the character of this error character and front and back to find out the most logical character from character data, replace described error character.
6. the method for automatic identification invoice according to claim 1, is characterized in that,, described step S5) comprising: according to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is replaced described error character by the most similar character of font in described character database.
7. automatically identify a device for invoice, it is characterized in that, comprising:
Image collection module, described image collection module is for obtaining invoice to be identified image after optical scanning;
Pretreatment module, described pretreatment module is for carrying out pre-service to described picture;
Space of a whole page locating module, described space of a whole page locating module is for carrying out space of a whole page location to described pretreated image;
Identification module, described identification module is for carrying out character recognition to the character of space of a whole page location;
Checking module, described checking module is for the character identifying is carried out to aftertreatment and check and correction, thus acquisition invoice number.
8. the device of automatic identification invoice according to claim 7, is characterized in that, described image collection module comprises the scan module that adopts OCR technology to scan invoice.
9. the device of automatic identification invoice according to claim 7, is characterized in that, described pretreatment module is configured to described image to carry out binaryzation, noise removal and slant correction.
10. the device of automatic identification invoice according to claim 7, is characterized in that, described space of a whole page identification module is configured to:
1) according to invoice type, set space of a whole page identified region;
2) to this regional assignment two-dimensional coordinate;
3) character in this region is identified.
The device of 11. automatic identification invoices according to claim 7, is characterized in that, described checking module is configured to:
According to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is concentrated the logicality of the character of this error character and front and back to find out the most logical character from character data, replace described error character.
The device of 12. automatic identification invoices according to claim 7, is characterized in that, described checking module is configured to:
According to the described character identifying, whether belong to predetermined character database and judge whether to belong to error character; If error character is replaced described error character by the most similar character of font in described character database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310582905.XA CN103617415A (en) | 2013-11-19 | 2013-11-19 | Device and method for automatically identifying invoice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310582905.XA CN103617415A (en) | 2013-11-19 | 2013-11-19 | Device and method for automatically identifying invoice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103617415A true CN103617415A (en) | 2014-03-05 |
Family
ID=50168118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310582905.XA Pending CN103617415A (en) | 2013-11-19 | 2013-11-19 | Device and method for automatically identifying invoice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103617415A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299311A (en) * | 2014-10-16 | 2015-01-21 | 浪潮软件集团有限公司 | Method for self-service invoice verification through two-dimensional code |
| CN104992495A (en) * | 2015-07-09 | 2015-10-21 | 胡昭 | Cloud intelligent invoice examination self-service terminal, and examination system and method thereof based on the same |
| CN105005793A (en) * | 2015-07-15 | 2015-10-28 | 广州敦和信息技术有限公司 | Method and device for automatically identifying and recording invoice character strip |
| CN105160713A (en) * | 2015-08-25 | 2015-12-16 | 安徽味唯网络科技有限公司 | Receipt-based parking fee waiving method in unmanned parking lot |
| 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 |
| CN105678301A (en) * | 2016-01-05 | 2016-06-15 | 珠海全志科技股份有限公司 | Method, system and device for automatically identifying and segmenting text image |
| CN106650715A (en) * | 2016-10-26 | 2017-05-10 | 西安电子科技大学 | Method for detecting and correcting errors of OCR recognition results of character strings according to permission set |
| CN106934918A (en) * | 2015-12-30 | 2017-07-07 | 航天信息股份有限公司 | The method and apparatus for carrying out bill character recognition using basic corpus auxiliary |
| CN107016363A (en) * | 2017-03-30 | 2017-08-04 | 理光图像技术（上海）有限公司 | Bill images managing device, bill images management system and method |
| CN103995904B (en) * | 2014-06-13 | 2017-09-12 | 上海珉智信息科技有限公司 | A kind of identifying system of image file electronic bits of data |
| CN107194400A (en) * | 2017-05-31 | 2017-09-22 | 北京天宇星空科技有限公司 | A kind of finance reimbursement unanimous vote is according to picture recognition processing method |
| CN107517272A (en) * | 2017-09-14 | 2017-12-26 | 新疆圣力信息科技有限公司 | A kind of device, the system and method for automatic data collection set form data |
| CN107767193A (en) * | 2016-08-23 | 2018-03-06 | 北京京东尚科信息技术有限公司 | A kind of method for managing invoice |
| CN108108732A (en) * | 2016-11-25 | 2018-06-01 | 财团法人工业技术研究院 | Character recognition system and character recognition method thereof |
| CN108133212A (en) * | 2018-01-05 | 2018-06-08 | 东华大学 | A kind of quota invoice amount identifying system based on deep learning |
| CN108460418A (en) * | 2018-03-07 | 2018-08-28 | 南京邮电大学 | A kind of invoice sorting technique based on Text region and semantic analysis |
| WO2018233171A1 (en) * | 2017-06-23 | 2018-12-27 | 平安科技（深圳）有限公司 | Method and apparatus for entering document information, computer device and 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 |
| CN109426815A (en) * | 2017-08-22 | 2019-03-05 | 顺丰科技有限公司 | A kind of rotation of document field and cutting method, system, equipment |
| CN109741517A (en) * | 2018-12-26 | 2019-05-10 | 大象慧云信息技术有限公司 | A kind of invoice checking method, device and system |
| CN109766778A (en) * | 2018-12-19 | 2019-05-17 | 平安科技（深圳）有限公司 | Invoice information input method, device, equipment and storage medium based on OCR technique |
| CN109919147A (en) * | 2019-03-04 | 2019-06-21 | 上海宝尊电子商务有限公司 | The method of text identification in drop for clothing image |
| CN110458997A (en) * | 2018-05-07 | 2019-11-15 | 北京中海汇银财税服务有限公司 | A kind of method and system of automatic pinging electronic invoice |
| CN110717366A (en) * | 2018-07-13 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Text information identification method, device, equipment and storage medium |
| CN112213312A (en) * | 2019-07-10 | 2021-01-12 | 云账户技术(天津)有限公司 | Automatic batch invoice quality detection system and detection method thereof |
Citations (4)
| 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 |
| CN1815490A (en) * | 2005-02-01 | 2006-08-09 | 佳能株式会社 | Data processing apparatus, image processing apparatus, data processing method, image processing method |
| CN102737242A (en) * | 2012-06-12 | 2012-10-17 | 丰豪盈彩（北京）科技有限公司 | Automatic bill recognition method and system applied to mobile terminal |
| 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 |
-
2013
- 2013-11-19 CN CN201310582905.XA patent/CN103617415A/en active Pending
Patent Citations (4)
| 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 |
| CN1815490A (en) * | 2005-02-01 | 2006-08-09 | 佳能株式会社 | Data processing apparatus, image processing apparatus, data processing method, image processing method |
| 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 |
| CN102737242A (en) * | 2012-06-12 | 2012-10-17 | 丰豪盈彩（北京）科技有限公司 | Automatic bill recognition method and system applied to mobile terminal |
Non-Patent Citations (1)
| Title |
|---|
| 贾彦金，黄照: "票据印刷号码定位识别技术研究", 《包装工程》, vol. 31, no. 1, 31 January 2010 (2010-01-31), pages 76 - 78 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995904B (en) * | 2014-06-13 | 2017-09-12 | 上海珉智信息科技有限公司 | A kind of identifying system of image file electronic bits of data |
| CN104299311A (en) * | 2014-10-16 | 2015-01-21 | 浪潮软件集团有限公司 | Method for self-service invoice verification through two-dimensional code |
| 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 |
| CN104992495A (en) * | 2015-07-09 | 2015-10-21 | 胡昭 | Cloud intelligent invoice examination self-service terminal, and examination system and method thereof based on the same |
| CN105005793B (en) * | 2015-07-15 | 2018-02-27 | 广州敦和信息技术有限公司 | A kind of method and device of invoice brief note automatic identification typing |
| CN105005793A (en) * | 2015-07-15 | 2015-10-28 | 广州敦和信息技术有限公司 | Method and device for automatically identifying and recording invoice character strip |
| CN105160713A (en) * | 2015-08-25 | 2015-12-16 | 安徽味唯网络科技有限公司 | Receipt-based parking fee waiving method in unmanned parking lot |
| CN106934918A (en) * | 2015-12-30 | 2017-07-07 | 航天信息股份有限公司 | The method and apparatus for carrying out bill character recognition using basic corpus auxiliary |
| CN105678301A (en) * | 2016-01-05 | 2016-06-15 | 珠海全志科技股份有限公司 | Method, system and device for automatically identifying and segmenting text image |
| CN105678301B (en) * | 2016-01-05 | 2019-12-13 | 珠海全志科技股份有限公司 | method, system and device for automatically identifying and segmenting text image |
| CN107767193A (en) * | 2016-08-23 | 2018-03-06 | 北京京东尚科信息技术有限公司 | A kind of method for managing invoice |
| CN106650715A (en) * | 2016-10-26 | 2017-05-10 | 西安电子科技大学 | Method for detecting and correcting errors of OCR recognition results of character strings according to permission set |
| CN108108732B (en) * | 2016-11-25 | 2022-01-11 | 财团法人工业技术研究院 | Character recognition system and character recognition method thereof |
| CN108108732A (en) * | 2016-11-25 | 2018-06-01 | 财团法人工业技术研究院 | Character recognition system and character recognition method thereof |
| CN107016363B (en) * | 2017-03-30 | 2020-06-05 | 理光图像技术（上海）有限公司 | Bill image management device, bill image management system, and bill image management method |
| CN107016363A (en) * | 2017-03-30 | 2017-08-04 | 理光图像技术（上海）有限公司 | Bill images managing device, bill images management system and method |
| CN107194400A (en) * | 2017-05-31 | 2017-09-22 | 北京天宇星空科技有限公司 | A kind of finance reimbursement unanimous vote is according to picture recognition processing method |
| CN107194400B (en) * | 2017-05-31 | 2019-12-20 | 北京天宇星空科技有限公司 | Financial reimbursement full ticket image recognition processing method |
| WO2018233171A1 (en) * | 2017-06-23 | 2018-12-27 | 平安科技（深圳）有限公司 | Method and apparatus for entering document information, computer device and 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 |
| CN109426815A (en) * | 2017-08-22 | 2019-03-05 | 顺丰科技有限公司 | A kind of rotation of document field and cutting method, 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 |
| CN109426815B (en) * | 2017-08-22 | 2022-05-10 | 顺丰科技有限公司 | Bill region rotating and splitting method, system and equipment |
| CN107517272A (en) * | 2017-09-14 | 2017-12-26 | 新疆圣力信息科技有限公司 | A kind of device, the system and method for automatic data collection set form data |
| CN108133212B (en) * | 2018-01-05 | 2021-06-29 | 东华大学 | Quota invoice amount recognition system based on deep learning |
| CN108133212A (en) * | 2018-01-05 | 2018-06-08 | 东华大学 | A kind of quota invoice amount identifying system based on deep learning |
| CN108460418A (en) * | 2018-03-07 | 2018-08-28 | 南京邮电大学 | A kind of invoice sorting technique based on Text region and semantic analysis |
| CN108460418B (en) * | 2018-03-07 | 2021-09-28 | 南京邮电大学 | Invoice classification method based on character recognition and semantic analysis |
| CN110458997A (en) * | 2018-05-07 | 2019-11-15 | 北京中海汇银财税服务有限公司 | A kind of method and system of automatic pinging electronic invoice |
| CN110717366A (en) * | 2018-07-13 | 2020-01-21 | 杭州海康威视数字技术股份有限公司 | Text information identification method, device, equipment and storage medium |
| CN109766778A (en) * | 2018-12-19 | 2019-05-17 | 平安科技（深圳）有限公司 | Invoice information input method, device, equipment and storage medium based on OCR technique |
| CN109741517A (en) * | 2018-12-26 | 2019-05-10 | 大象慧云信息技术有限公司 | A kind of invoice checking method, device and system |
| CN109919147A (en) * | 2019-03-04 | 2019-06-21 | 上海宝尊电子商务有限公司 | The method of text identification in drop for clothing image |
| CN112213312A (en) * | 2019-07-10 | 2021-01-12 | 云账户技术(天津)有限公司 | Automatic batch invoice quality detection system and detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103617415A (en) | Device and method for automatically identifying invoice | |
| US10943105B2 (en) | Document field detection and parsing | |
| CN101908136B (en) | Table identifying and processing method and system | |
| CN107358232B (en) | Invoice identification method based on plug-in | |
| CN108717545B (en) | Bill identification method and system based on mobile phone photographing | |
| CN101458770B (en) | Character recognition method and system | |
| CN111476109A (en) | Bill processing method, bill processing apparatus, and computer-readable storage medium | |
| CN104217203B (en) | Complex background card face information identifying method and system | |
| CN103295034B (en) | A kind of embedded Books Chaotic Frame checking system based on DSP and method | |
| US7970213B1 (en) | Method and system for improving the recognition of text in an image | |
| CN107423732A (en) | Vehicle VIN recognition methods based on Android platform | |
| CN105528604A (en) | Bill automatic identification and processing system based on OCR | |
| CN110929580A (en) | Financial statement information rapid extraction method and system based on OCR | |
| CN113158895B (en) | Bill identification method and device, electronic equipment and storage medium | |
| Sidhwa et al. | Text extraction from bills and invoices | |
| US20140268250A1 (en) | Systems and methods for receipt-based mobile image capture | |
| CN112418812A (en) | Distributed full-link automatic intelligent clearance system, method and storage medium | |
| CN112686257A (en) | Storefront character recognition method and system based on OCR | |
| CN113963147A (en) | Key information extraction method and system based on semantic segmentation | |
| CN111858977B (en) | Bill information acquisition method, device, computer equipment and storage medium | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| WO2017069741A1 (en) | Digitized document classification | |
| CN116363655A (en) | Financial bill identification method and system | |
| CN112348022B (en) | Free-form document identification method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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: 20140305 |
|
| RJ01 | Rejection of invention patent application after publication |