Identification method based on classifiers in image document electronic material identification system

A recognition method and recognition system technology, applied in the field of classifier recognition, can solve problems such as character sticking, incomplete recognition information, frequent changes in font size, etc., to achieve the effect of improving recognition efficiency, reducing workload, and ensuring full reliability

Inactive Publication Date: 2014-08-20
SHANGHAI MINZHI INFORMATION TECH
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of the bill layout and the particularity of the recognition requirements, various difficulties may be encountered in the actual system: there are interference information such as stamps, inks, handwritten information, background patterns, etc. on the bill layout; There are problems such as character sticking, frequent font size changes, and incomplete identification information

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification method based on classifiers in image document electronic material identification system
  • Identification method based on classifiers in image document electronic material identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention uses such as figure 1 The image file electronic data recognition system shown in the figure recognizes the information of the image obtained by scanning the paper document, forms an electronic file matching the information, and stores it in the database for subsequent query by users. The recognition system mainly includes: a preprocessing module including binarization and other preprocessing for the scanned image; extracting the recognition area from the image, segmenting the text lines, and removing the interference information (such as seals, handwriting, background patterns) , shading, noise, etc.) layout analysis module; information recognition module that recognizes the characters in the recognition area in the image; classifier that classifies the recognized information according to different types; corrects the recognized information according to the classification results information correction module.

[0023] The layout analysis module o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an identification method based on classifiers in an image document electronic material identification system. The classifiers are arranged in the identification system, identification information of images is classified to obtain different information items, corresponding lookup tables are built for all information items, and the identification information is compared through content in the lookup tables. The method can automatically identify the scanning images, useful information is extracted from the scanning images and is stored in a database according to a certain classifying rule for user searching and inquiring, and workloads of users are reduced to the maximum extent. The rate of identification of characters is improved through a multi-classifier fusion method; a format template is adopted, the content of the different information items are compared through a multi-region and multi-content redundancy check method, the sufficient reliability of an identification result is ensured, and the identification efficiency is improved.

Description

technical field [0001] The invention relates to the field of data management systems, in particular to a method for identifying classifiers in an electronic data identification system based on image files. Background technique [0002] In modern society, paper documents (such as bank vouchers, personal information forms, etc.) are still widely used, and it is very difficult to store and manage paper documents, and to classify and find information on documents. The popularity of computers and smart phones has made it possible to manage paper documents electronically, but it takes a lot of time and manpower to manually input the information on paper documents into the electronic system; and the automatic identification of bill content through intelligent systems is still There are many limitations. [0003] For example, in banking business, a large amount of information on the bills are printed numbers and Chinese and English characters. Accurate extraction and identification...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
Inventor 林珉
Owner SHANGHAI MINZHI INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap