CN112541772A - Merchant-oriented qualification authentication method - Google Patents
Merchant-oriented qualification authentication method Download PDFInfo
- Publication number
- CN112541772A CN112541772A CN202011397985.8A CN202011397985A CN112541772A CN 112541772 A CN112541772 A CN 112541772A CN 202011397985 A CN202011397985 A CN 202011397985A CN 112541772 A CN112541772 A CN 112541772A
- Authority
- CN
- China
- Prior art keywords
- shop
- image
- merchant
- text
- characters
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
- G06V20/39—Urban scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention discloses a qualification authentication method facing a merchant, which belongs to the technical field of artificial intelligent optical character recognition, and is characterized in that the image filtering is carried out by shooting a shop billboard to eliminate noise mixed in the image; detecting characters in the image by adopting a character detection model, determining coordinate areas of the characters in the image, identifying the characters in each coordinate area by adopting a character identification model, and identifying and extracting shop names in the characters by adopting a named entity; meanwhile, by means of the position information of the shop, the merchant is positioned in the database, and the identity information and the business information of the shop employees are obtained. The invention can quickly identify the names of shops and inquire the information of employees, quickly check the qualification of the employees, stop the operation without evidence and comprehensively improve the job-performing capability of law enforcement officers.
Description
Technical Field
The invention relates to the technical field of artificial intelligence optical character recognition, in particular to a qualification authentication method facing to a merchant.
Background
The digital government is a novel government operation mode, further optimizes and adjusts organization structure, operation program and management service in the government by constructing a new government affair mechanism, a new platform and a new channel driven by big data, comprehensively improves the job-keeping capability of the government in the fields of economic regulation, market supervision, social management, public service, environmental protection and the like, and forms a modern management mode of 'data conversation, data decision, data service and data innovation'.
The establishment of local government big data authorities indicates that governments have fully recognized the importance of big data, so that governments are helped to better arrange and collect data, data fusion and data sharing are realized, and continuous fuel is provided for digital government construction. How to better apply the big data to the fields of economic regulation, market supervision, social governance, public service, environmental protection and the like has important significance for digital government administration.
Disclosure of Invention
The technical task of the invention is to provide a qualification authentication method facing to the commercial tenant aiming at the defects, which can quickly identify the name of the commercial tenant and inquire the information of the personnel, quickly check the qualification of the personnel, avoid the operation without certificate and comprehensively improve the job-carrying capacity of the law enforcement personnel.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a qualification authentication method facing a merchant is characterized in that the image filtering is carried out by shooting a shop billboard to eliminate noise mixed in the image; detecting characters in the image by adopting a character detection model, determining coordinate areas of the characters in the image, identifying the characters in each coordinate area by adopting a character identification model, and identifying and extracting shop names in the characters by adopting a named entity; meanwhile, by means of the position information of the shop, the merchant is positioned in the database, and the identity information and the business information of the shop employees are obtained.
The method is based on commercial tenant billboard character recognition, commercial tenants are quickly positioned in the database by recognizing the store names in the commercial tenant billboards and with the help of the position information of the stores, so that the identity information of the office workers and the business license information are obtained, government law enforcement workers can conveniently and quickly authenticate the identity of the commercial tenants, the non-certified operation is prevented, and the law enforcement efficiency is improved.
Preferably, the image filtering is to eliminate gaussian noise by using gaussian filtering, scan each pixel in the image by using a mask, and replace the value of the central pixel point of the template by using the weighted average gray value of the pixels in the neighborhood determined by the mask, thereby eliminating noise mixed in the image.
Preferably, characters in the image are detected by adopting a character detection model built based on a Tensorflow deep learning framework, a coordinate region of the characters in the image is determined, and the coordinates of four vertexes of the quadrangular text region are obtained by detecting the text including Chinese and English types and the text region arranged horizontally and vertically.
Furthermore, the character detection model identifies characters in each text region picture through a character identification module, wherein the characters comprise Chinese, English, numbers and punctuation marks;
the character recognition module comprises a characteristic extraction part and a character prediction part,
the characteristic extraction part is composed of a plurality of convolution layers and is responsible for extracting deep-level characteristics of the image;
the character prediction part is composed of a cyclic neural network, and the bidirectional LSTM is used for processing the problem of prediction of an indefinite length sequence and predicting an indefinite length text.
Preferably, the character detection model comprises a feature extraction module, a feature fusion module and an output module;
the feature extraction module is composed of a plurality of convolution layers and used for extracting deep features of the image;
the characteristic fusion module is used for fusing the characteristics generated by the characteristic extraction module, solving the problems that the detection of a large text area is inaccurate and the detection of a small text area is not realized, fusing the characteristics of different receptive fields and supplementing target information with different sizes to realize the detection of objects with different sizes;
the content output by the output module comprises the confidence of the output text, namely the probability of the pixel points in the text box; outputting the probability that the pixel point is positioned at the boundary of the text box and at the head or the tail of the text box; and outputting the upper left (upper right) X coordinate, the upper left (upper right) Y coordinate, the lower left (lower right) X coordinate and the lower left (lower right) Y coordinate of the text box.
Furthermore, because the shop billboard may have characters except the shop name, the shop name needs to be extracted from all the recognized characters, the shop name is recognized by adopting a named entity recognition technology based on a jieba word segmentation module, all the shop names in the database are used as a user-defined dictionary, the shop names are loaded into the jieba Chinese word segmentation module by taking the shop as a part of speech, and the characters recognized by the character recognition module are segmented, so that the segmentation with the part of speech being the shop, namely the shop name, is obtained.
Preferably, due to the possibility of duplicate names of the store names in different areas, when the merchant needs to be located in the database, the database is searched by means of the position information and the name of the store, the location is accurately located, and the identity information and business information of the store staff, including the personal basic information and the business license information, are obtained.
Further, the law enforcement officer carries out qualification authentication on the practitioner according to the information inquired from the database.
The invention also claims a merchant-oriented qualification certification device, comprising: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is used for calling the machine readable program and executing the method.
The invention also claims a computer readable medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the above-described method.
Compared with the prior art, the qualification authentication method facing the commercial tenant has the following beneficial effects:
the method aims at the authentication method for rapidly and intelligently authenticating the qualification of the commercial tenant of the government law enforcement officer, the content of the advertising board is intelligently identified by shooting the shop advertising board, the name of the shop is extracted from the identified text content, and then the database is inquired according to the name of the shop to acquire the relevant information of the practitioner officer, so that the data is used for speaking, the data decision is used, and the function-performing capability of the law enforcement officer is comprehensively improved.
The method improves the job-carrying capacity of the government in the fields of economic regulation, market supervision, social governance, public service, environmental protection and the like by relying on the construction work of government administration and even digital governments, forms a modern governance mode of data conversation, data decision, data service and data innovation, quickly identifies the names of shops, inquires the information of employees, quickly checks the qualification of the employees and stops the operation without evidence.
The artificial intelligence technology is combined with government affair big data to achieve government affair service intellectualization and informatization, flow efficiency and service quality of government affair service are improved, and accordingly flexible and telescopic government service, data-driven government service and intelligent and efficient government service are achieved.
Drawings
Fig. 1 is a flowchart of a method for authenticating a merchant-oriented qualification according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
In recent years, artificial intelligence technology has been rapidly developed, and technologies such as character recognition, face recognition, image analysis, voice recognition and the like have been commercially applied.
The artificial intelligence technology is combined with government affair big data to achieve government affair service intellectualization and informatization, flow efficiency and service quality of government affair service are improved, and then flexible and telescopic government service, data-driven government service and intelligent and efficient government service are achieved.
The embodiment of the invention provides a merchant-oriented qualification authentication method, which comprises the steps of shooting a shop billboard, intelligently identifying the content of the billboard, extracting a shop name from the identified text content, and further querying a database according to the shop name to obtain relevant information of employees, so that data talking and data decision are realized, and the job-performing capability of law enforcement officers is comprehensively improved.
In the method, the image filtering is carried out by shooting the shop billboard, so as to eliminate the noise mixed in the image; detecting characters in the image by adopting a character detection model, determining coordinate areas of the characters in the image, identifying the characters in each coordinate area by adopting a character identification model, and identifying and extracting shop names in the characters by adopting a named entity; meanwhile, by means of the position information of the shop, the merchant is positioned in the database, the identity information and business information of the shop employees are obtained, the government law enforcement officers can conveniently and quickly authenticate the identity of the merchant, the non-certified operation is prevented, and the law enforcement efficiency is improved.
And the image filtering adopts Gaussian filtering to eliminate Gaussian noise, each pixel in the image is scanned by using a mask, and the weighted average gray value of the pixels in the neighborhood determined by the mask is used for replacing the value of the central pixel point of the template to eliminate noise mixed in the image.
The character detection model is a deep network model built on the basis of a Tensorflow deep learning framework, is responsible for detecting text regions in images, can detect Chinese and English type texts, can detect horizontally and vertically arranged text regions, and obtains coordinates of four vertexes of a quadrangular text region.
The character recognition model is based on a deep network model built by a Tensorflow deep learning framework, performs text recognition on images in quadrilateral text regions, and has the capacity of recognizing Chinese, English, numbers and punctuation marks.
The shop names in the extracted characters are identified by adopting the named entities, all the shop names in the database are used as a user-defined dictionary, the shop names are loaded into the jieba Chinese word segmentation module by taking the shop names as parts of speech, and the words identified by the character identification module are segmented, so that the segmented words with the parts of speech being the shop names are obtained.
The embodiment of the invention provides a qualification authentication method facing a merchant, which comprises the following specific implementation processes:
1) firstly, shooting a shop billboard, carrying out Gaussian filtering on the image, scanning each pixel in the image by using a mask, and replacing the value of a central pixel point of a template by using a weighted average gray value of pixels in a neighborhood determined by the mask to eliminate noise mixed in the image.
2) And then detecting characters in the image by adopting a character detection model built based on a Tensorflow deep learning framework, determining a coordinate region of the characters in the image, detecting Chinese and English type texts, detecting horizontally and vertically arranged text regions, and obtaining coordinates of four vertexes of the quadrangular text region.
The character detection model comprises a feature extraction module, a feature fusion module and an output module;
the feature extraction module is composed of a plurality of convolution layers and used for extracting deep features of the image;
the characteristic fusion module is used for fusing the characteristics generated by the characteristic extraction module, solving the problems that the detection of a large text area is inaccurate and the detection of a small text area is not realized, fusing the characteristics of different receptive fields and supplementing target information with different sizes to realize the detection of objects with different sizes;
the content output by the output module comprises three parts: the confidence of the output text, namely the probability of the pixel points in the text box; outputting the probability that the pixel point is positioned at the boundary of the text box and at the head or the tail of the text box; and outputting the upper left (upper right) X coordinate, the upper left (upper right) Y coordinate, the lower left (lower right) X coordinate and the lower left (lower right) Y coordinate of the text box.
3) On the basis that the character detection model identifies the character region, the character identification model built based on the Tensorflow deep learning framework is responsible for identifying characters in each text region picture, and has the capacity of identifying Chinese, English, numbers and punctuation marks.
The character recognition module consists of a feature extraction module and a character prediction module:
the feature extraction module is composed of a plurality of convolution layers and is responsible for extracting deep features of the image;
the character prediction module is composed of a cyclic neural network, and uses bidirectional LSTM to process the problem of prediction of indefinite length sequences and predict indefinite length texts.
4) Because characters except the shop names may exist in the shop billboard, the shop names need to be extracted from all the identified characters, and the shop names are identified by adopting a named entity identification technology based on a jieba word segmentation module. The shop name is used as a user-defined dictionary, and the shop is loaded into the jieba Chinese word segmentation module by taking the shop as a part of speech, and words are segmented on the words identified by the word identification module, so that words with the part of speech being the shop name are obtained.
5) Due to the possibility of duplicate names of stores in different areas, the database needs to be searched by means of the position information of the stores and the names of the stores simultaneously, and the information of the staff of the stores, including the personal basic information and the business license information, needs to be accurately located.
6) And finally, performing qualification authentication on the practitioner by the law enforcement officer according to the information inquired from the database.
The method relies on government affair big data and artificial intelligence technology, rapidly identifies the names of shops, queries the information of employees, rapidly checks the qualification of the employees, stops the operation without evidence, truly realizes speaking by data and decision making by data, and comprehensively improves the job-carrying capacity of law enforcement officers.
The embodiment of the invention also provides a device for authenticating the qualification facing the commercial tenant, which comprises: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine-readable program to execute the method for authenticating the merchant-oriented qualification in the above embodiment of the present invention.
An embodiment of the present invention further provides a computer-readable medium, where the computer-readable medium stores computer instructions, and when the computer instructions are executed by a processor, the processor is caused to execute the method for authenticating the merchant-oriented qualification described in the above embodiment of the present invention. Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
While the invention has been shown and described in detail in the drawings and in the preferred embodiments, it is not intended to limit the invention to the embodiments disclosed, and it will be apparent to those skilled in the art that various combinations of the code auditing means in the various embodiments described above may be used to obtain further embodiments of the invention, which are also within the scope of the invention.
Claims (10)
1. A qualification authentication method facing a merchant is characterized in that the method comprises the steps of shooting a shop billboard, carrying out image filtering, and eliminating noise mixed in an image; detecting characters in the image by adopting a character detection model, determining coordinate areas of the characters in the image, identifying the characters in each coordinate area by adopting a character identification model, and identifying and extracting shop names in the characters by adopting a named entity; meanwhile, by means of the position information of the shop, the merchant is positioned in the database, and the identity information and the business information of the shop employees are obtained.
2. The merchant-oriented qualification method of claim 1, wherein the image filtering is performed by using gaussian filtering, each pixel in the image is scanned by using a mask, and the weighted average gray value of the pixels in the neighborhood determined by the mask is used to replace the value of the central pixel point of the template, so as to eliminate noise mixed in the image.
3. The merchant-oriented qualification authentication method as claimed in claim 1, wherein a character detection model built based on a Tensorflow deep learning framework is used for detecting characters in an image, a coordinate region of the characters in the image is determined, the detection comprises detecting Chinese and English type texts and detecting horizontally and vertically arranged text regions, and coordinates of four vertexes of a quadrangular text region are obtained.
4. The merchant-oriented qualification authentication method as claimed in claim 3, wherein the text detection model identifies the text in each text region picture by a text identification module, wherein the text comprises Chinese, English, numeral and punctuation marks;
the character recognition module comprises a characteristic extraction part and a character prediction part,
the characteristic extraction part is composed of a plurality of convolution layers and is responsible for extracting deep-level characteristics of the image;
the character prediction part is composed of a cyclic neural network, and the bidirectional LSTM is used for processing the problem of prediction of an indefinite length sequence and predicting an indefinite length text.
5. The merchant-oriented qualification authentication method according to claim 1, 3 or 4, wherein the text detection model comprises a feature extraction module, a feature fusion module and an output module;
the feature extraction module is composed of a plurality of convolution layers and used for extracting deep features of the image;
the characteristic fusion module is used for fusing the characteristics generated by the characteristic extraction module, fusing the characteristics of different receptive fields and supplementing target information of different sizes to realize the detection of objects of different sizes;
the output content of the output module comprises the confidence coefficient of the output text, the probability that the output pixel point is positioned at the boundary of the text box and at the head or the tail of the text box, and the upper left (upper right) X coordinate, the upper left (upper right) Y coordinate, the lower left (lower right) X coordinate and the lower left (lower right) Y coordinate of the output text box.
6. The merchant-oriented qualification authentication method according to claim 1, 3 or 4, wherein a name of a shop is recognized by using a named entity recognition technology based on a jieba word segmentation module, the shop name is used as a user-defined dictionary, and a shop is loaded into a jieba Chinese word segmentation module by using a shop as a part of speech, and words recognized by the word recognition module are segmented, so that words with the part of speech being the shop are obtained, namely the shop name.
7. The method as claimed in claim 1, wherein when the business is located in the database, the identity information and business information of the business personnel in the store, including the personal basic information and the business license information, are obtained by means of the location information and the name of the business.
8. The merchant-oriented qualification method according to claim 1 or 7, wherein law enforcement officers perform qualification on the employees according to the information queried from the database.
9. A merchant-oriented qualification apparatus, comprising: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor, configured to invoke the machine readable program to perform the method of any of claims 1 to 8.
10. Computer readable medium, characterized in that it has stored thereon computer instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011397985.8A CN112541772A (en) | 2020-12-04 | 2020-12-04 | Merchant-oriented qualification authentication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011397985.8A CN112541772A (en) | 2020-12-04 | 2020-12-04 | Merchant-oriented qualification authentication method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112541772A true CN112541772A (en) | 2021-03-23 |
Family
ID=75015517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011397985.8A Pending CN112541772A (en) | 2020-12-04 | 2020-12-04 | Merchant-oriented qualification authentication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541772A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268762A (en) * | 2014-09-28 | 2015-01-07 | 吉林找它信息有限公司 | Information inquiry system |
| CN104933068A (en) * | 2014-03-19 | 2015-09-23 | 阿里巴巴集团控股有限公司 | Method and device for information searching |
| CN105930335A (en) * | 2016-03-31 | 2016-09-07 | 石平安 | Browser system based on or including corporate credit module |
| CN110223050A (en) * | 2019-06-24 | 2019-09-10 | 广东工业大学 | A kind of verification method and relevant apparatus of merchant store fronts title |
| CN110363199A (en) * | 2019-07-16 | 2019-10-22 | 济南浪潮高新科技投资发展有限公司 | Certificate image text recognition method and system based on deep learning |
| CN111382744A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Shop information acquisition method and device, terminal equipment and storage medium |
| CN111428656A (en) * | 2020-03-27 | 2020-07-17 | 信雅达系统工程股份有限公司 | Mobile terminal identity card identification method based on deep learning and mobile device |
| CN111553355A (en) * | 2020-05-18 | 2020-08-18 | 城云科技（中国）有限公司 | Method for detecting out-of-store operation and notifying management shop owner based on monitoring video |
| KR102166044B1 (en) * | 2020-03-31 | 2020-10-15 | 주식회사 와이케이프렌즈 | System for providing kids cafe management service using freepass membership |
-
2020
- 2020-12-04 CN CN202011397985.8A patent/CN112541772A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933068A (en) * | 2014-03-19 | 2015-09-23 | 阿里巴巴集团控股有限公司 | Method and device for information searching |
| CN104268762A (en) * | 2014-09-28 | 2015-01-07 | 吉林找它信息有限公司 | Information inquiry system |
| CN105930335A (en) * | 2016-03-31 | 2016-09-07 | 石平安 | Browser system based on or including corporate credit module |
| CN111382744A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Shop information acquisition method and device, terminal equipment and storage medium |
| CN110223050A (en) * | 2019-06-24 | 2019-09-10 | 广东工业大学 | A kind of verification method and relevant apparatus of merchant store fronts title |
| CN110363199A (en) * | 2019-07-16 | 2019-10-22 | 济南浪潮高新科技投资发展有限公司 | Certificate image text recognition method and system based on deep learning |
| CN111428656A (en) * | 2020-03-27 | 2020-07-17 | 信雅达系统工程股份有限公司 | Mobile terminal identity card identification method based on deep learning and mobile device |
| KR102166044B1 (en) * | 2020-03-31 | 2020-10-15 | 주식회사 와이케이프렌즈 | System for providing kids cafe management service using freepass membership |
| CN111553355A (en) * | 2020-05-18 | 2020-08-18 | 城云科技（中国）有限公司 | Method for detecting out-of-store operation and notifying management shop owner based on monitoring video |
Non-Patent Citations (1)
| Title |
|---|
| 蒋加伏 等: "《Python程序设计基础》", 北京邮电大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543690B (en) | Method and device for extracting information | |
| Ryan et al. | An examination of character recognition on ID card using template matching approach | |
| CN111191695A (en) | Website picture tampering detection method based on deep learning | |
| JPWO2010092952A1 (en) | Pattern recognition device | |
| CN112508011A (en) | OCR (optical character recognition) method and device based on neural network | |
| CN112766255A (en) | Optical character recognition method, device, equipment and storage medium | |
| CN109766891A (en) | Obtain the method and computer readable storage medium of installations and facilities information | |
| CN110516676A (en) | A kind of bank's card number identifying system based on image procossing | |
| CN112232354A (en) | Character recognition method, device, equipment and storage medium | |
| CN112232336A (en) | Certificate identification method, device, equipment and storage medium | |
| CN110197140B (en) | Material auditing method and equipment based on character recognition | |
| CN114445836A (en) | Information auditing method and device combining RPA and AI and electronic equipment | |
| Sharma et al. | Automatic number plate recognition and parking management | |
| CN111881900B (en) | Corpus generation method, corpus translation model training method, corpus translation model translation method, corpus translation device, corpus translation equipment and corpus translation medium | |
| CN112541772A (en) | Merchant-oriented qualification authentication method | |
| Meng et al. | IRIS: smart phone aided intelligent reimbursement system using deep learning | |
| Siddique et al. | Development of an automatic vehicle license plate detection and recognition system for Bangladesh | |
| KR20210077251A (en) | Database building device that can build a knowledge database from a table-inserted image and operating method thereof | |
| CN113065559B (en) | Image comparison method and device, electronic equipment and storage medium | |
| CN116110066A (en) | Information extraction method, device and equipment of bill text and storage medium | |
| CN115439850A (en) | Image-text character recognition method, device, equipment and storage medium based on examination sheet | |
| CN116343237A (en) | Bill identification method based on deep learning and knowledge graph | |
| US11704924B2 (en) | Method, apparatus, and computer-readable storage medium for recognizing characters in a digital document | |
| CN110956174A (en) | Device number identification method | |
| Oosterman et al. | Geolocation on the iPhone by automatic street sign reading |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |