CN106709483A - Method of image recognition according to specified location - Google Patents
Method of image recognition according to specified location Download PDFInfo
- Publication number
- CN106709483A CN106709483A CN201510429706.4A CN201510429706A CN106709483A CN 106709483 A CN106709483 A CN 106709483A CN 201510429706 A CN201510429706 A CN 201510429706A CN 106709483 A CN106709483 A CN 106709483A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- block
- database
- specified location
- 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
Landscapes
- Character Discrimination (AREA)
- Character Input (AREA)
Abstract
The invention discloses a method of image recognition through reading a specified location. The method comprises the following steps: an image file is opened; a location in need of block content analysis is found out; and the block location information is saved to a database. According to the image recognition method of the invention, through finding out the location in need of block content analysis and saving the block location information to the database, image recognition according to the specified location can be carried out, data in need of analysis are intelligently extracted through a computer, and thus, the manpower cost is saved, happening of mistakes is avoided, the efficiency is improved, and the reliability is high.
Description
Technical field
The present invention relates to image-recognizing method, the method that image recognition is more particularly to carried out according to specified location.
Background technology
At present, patent agency uses manual typing for the reading and typing of information in various notices, and not systematic method carries out intelligent typing, and not only workload is big for manual entry, and error-prone.
Information on notice is graphic form, and current picture recognition technology can only read whole picture, the partial content on whole picture is not read, and the contents of the section is converted into text information and stored.
The content of the invention
The present invention solves the technical problem of providing a kind of method that image recognition is carried out according to specified location, can reduces cost, improve speed, simplify operation and with high reliability.
In order to solve the above technical problems, the technical method that the present invention is used is:There is provided a kind of according to the method that specified location carries out image recognition is read, the method is comprised the following steps:Open image file;Find out the position for wanting analysing content block;And block locations information is saved in database.
Wherein, the method for opening image file is to be opened with general pattern application program.
In order to solve the above technical problems, another technical solution used in the present invention is:A kind of method for processing and reading specified location image information is provided, this includes:The source file for needing analysis is read in circulation;Block positional information is read from database;According to block locations information identical image is replicated from the response position in source file;Image is processed and temporary file is saved as;The image in temporary file is identified using OCR technique;And the data of analysis are stored in database.
The beneficial effects of the invention are as follows:The situation of prior art is different from, image-recognizing method of the invention passes through to find out the position for wanting analysing content block;Block locations information is saved in database, image recognition can be carried out according to specified location, the data that will be analyzed are extracted by computer intelligence, so saved human cost, and avoid wrong generation, improve efficiency, reliability is high.
Brief description of the drawings
Fig. 1 is that the present invention carries out the flow chart of image-recognizing method according to specified location is read;
Fig. 2 is the flow chart that specified location image information method is read in present invention treatment.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
Fig. 1 is referred to, is that the present invention carries out the flow chart of image-recognizing method according to specified location is read.
The present embodiment carries out image-recognizing method and comprises the following steps according to reading specified location:
S101, opening image file.
Specifically, it is to be opened with general pattern application program to open image file method, and the general pattern application program includes PhotoShop, MSPaint.
For example, the image file can be the various notices of such as State Intellectual Property Office's hair, for example, accept notice, first time notification of examiner's opinion, patentable notice, etc..
S102, find out the position for wanting analysing content block.
According to above-mentioned example, for example in accepting notice, the important bibliographic information such as patent agency office or applicant's desired applying date that will be accepted in notice, application number, applicant, payment amount of money and payment project is crawled out automatically by computer, rather than during manual typing, needs find out the corresponding block locations of the project, and the position of these information is all fixed.Such as applying date, the upper left position (x1, y1) of block where applying date information and the coordinate of lower right position (x2, y2) can be found, that is, the position of the block is determined.
Specifically, the unit of above-mentioned location parameter can be pixel or inch.
S103, block locations information is saved in database.
Specifically, the information of block locations correspondence image is first converted into text information, for example, the applying date information in above-mentioned notice is converted into specific text information, the method for the conversion word is specially image is identified using OCR technique.
Fig. 2 is the flow chart that specified location image information method is read in present invention treatment.
The method that specified location image information is read in a kind for the treatment of of the present embodiment is comprised the following steps:The source file for needing analysis is read in S201, circulation.
S202, the reading block positional information from database.
S203, according to block locations information from source file response position replicate identical image.
S204, image is processed and temporary file is saved as.
S205, the image in temporary file is identified using OCR technique.
S206, the data of analysis are stored in database.
The present invention is different from prior art, image recognition can be carried out according to specified location, and the image of specified location is converted into text information to be stored in database, can so avoid manual typing information and cause information errors, brought to client or applicant brings unnecessary trouble, improve operating efficiency.
The foregoing is only embodiments of the present invention; not thereby the scope of the claims of the invention is limited; equivalent structure or equivalent flow conversion that every utilization description of the invention and accompanying drawing content are made; or other related technical fields are directly or indirectly used in, it is included within the scope of the present invention.
Claims (8)
1. it is a kind of according to reading the specified location method that carries out image recognition, it is characterised in that to comprise the following steps:
Open image file;
Find out the position for wanting analysing content block;And block locations information is saved in database.
2. method according to claim 1, it is characterised in that the method for the opening image file is to be opened with general pattern application program.
3. method according to claim 2, it is characterised in that the general pattern application program is including PhotoShop, MSPaint etc..
4. method according to claim 1, it is characterised in that it is described find out the position for wanting analysing content block method be the coordinate and the lower right corner that determine the block locations upper left corner coordinate.
5. method according to claim 1, it is characterised in that described being found out further include after the position step for wanting analysing content block and image information will be converted to text information in analysing content block.
6. method according to claim 1 or 5, it is characterised in that described block locations information is saved in block locations information in database to refer to text information in block locations.
7. method according to claim 5, it is characterised in that described image information to be converted to the method for text information and be specially and be identified to image using OCR technique in analysing content block.
8. it is a kind of to process the method for reading specified location image information, it is characterised in that to comprise the following steps:
The source file for needing analysis is read in circulation;
Block positional information is read from database;
According to block locations information, response position replicates identical image from source file;
Image is processed and temporary file is saved as;
The image in temporary file is identified using OCR technique;And
The data of analysis are stored in database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510429706.4A CN106709483A (en) | 2015-07-21 | 2015-07-21 | Method of image recognition according to specified location |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510429706.4A CN106709483A (en) | 2015-07-21 | 2015-07-21 | Method of image recognition according to specified location |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106709483A true CN106709483A (en) | 2017-05-24 |
Family
ID=58899926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510429706.4A Pending CN106709483A (en) | 2015-07-21 | 2015-07-21 | Method of image recognition according to specified location |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106709483A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340031A (en) * | 2020-02-25 | 2020-06-26 | 杭州测质成科技有限公司 | Equipment almanac target information extraction and identification system based on image identification and method thereof |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103597500A (en) * | 2011-06-29 | 2014-02-19 | 高通股份有限公司 | System and method for recognizing text information in object |
CN103996055A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Identification method based on classifiers in image document electronic material identification system |
CN104346615A (en) * | 2013-08-08 | 2015-02-11 | 北大方正集团有限公司 | Device and method for extracting composite graph in format document |
-
2015
- 2015-07-21 CN CN201510429706.4A patent/CN106709483A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103597500A (en) * | 2011-06-29 | 2014-02-19 | 高通股份有限公司 | System and method for recognizing text information in object |
CN104346615A (en) * | 2013-08-08 | 2015-02-11 | 北大方正集团有限公司 | Device and method for extracting composite graph in format document |
CN103996055A (en) * | 2014-06-13 | 2014-08-20 | 上海珉智信息科技有限公司 | Identification method based on classifiers in image document electronic material identification system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111340031A (en) * | 2020-02-25 | 2020-06-26 | 杭州测质成科技有限公司 | Equipment almanac target information extraction and identification system based on image identification and method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI386822B (en) | A method for establishing a multilingual translation data base rapidly | |
EP3816855A2 (en) | Method and apparatus for extracting information, device, storage medium and computer program product | |
US20210390299A1 (en) | Techniques to determine document recognition errors | |
WO2022178994A1 (en) | Table structure recognition method and apparatus, electronic device, and storage medium | |
CN112528013A (en) | Text abstract extraction method and device, electronic equipment and storage medium | |
CN112732567A (en) | Mock data testing method and device based on ip, electronic equipment and storage medium | |
US20070065017A1 (en) | Genetic family-tree object recognition | |
US9881004B2 (en) | Gender and name translation from a first to a second language | |
CN113360139A (en) | Integration method and device of front-end frame, electronic equipment and storage medium | |
CN106709483A (en) | Method of image recognition according to specified location | |
CN112560855A (en) | Image information extraction method and device, electronic equipment and storage medium | |
CN110287459B (en) | Form batch processing method, system, device and storage medium | |
CN109684395B (en) | Visual data interface universal analysis method based on natural language processing | |
JP2017111500A (en) | Character recognizing apparatus, and program | |
Koltun et al. | Information retrieval from redlined circuit diagrams and its model-based representation for automated engineering | |
CN115730603A (en) | Information extraction method, device, equipment and storage medium based on artificial intelligence | |
CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
CN113419951A (en) | Artificial intelligence model optimization method and device, electronic equipment and storage medium | |
CN113822215A (en) | Equipment operation guide file generation method and device, electronic equipment and storage medium | |
CN113850265A (en) | PDF document analysis method and device, electronic equipment and storage medium | |
CN103761247B (en) | A kind of processing method and processing device of error file | |
CN113821555A (en) | Unstructured data collection processing method of intelligent supervision black box | |
CN112989043A (en) | Reference resolution method and device, electronic equipment and readable storage medium | |
Rizi et al. | From Talent Shortage to Workforce Excellence in the CHIPS Act Era: Harnessing Industry 4.0 Paradigms for a Sustainable Future in Domestic Chip Production | |
CN107492354B (en) | Dot matrix liquid crystal generator set controller-based multi-language implementation method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170524 |
|
RJ01 | Rejection of invention patent application after publication |