Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Template Matching Method for Text Recognition Processing

A template matching and text recognition technology, applied in character recognition, character and pattern recognition, instruments, etc., can solve the problems of easy matching deviation, scale variability, sensitivity to illumination variability, etc., to improve the character recognition rate and solve wrinkles Effect

Inactive Publication Date: 2019-06-21
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, template matching also has its defects, that is, it is sensitive to the scale variability and illumination variability of the same type of characters in different scene images, and it is easy to cause matching deviation.

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
  • A Template Matching Method for Text Recognition Processing
  • A Template Matching Method for Text Recognition Processing
  • A Template Matching Method for Text Recognition Processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the implementation methods and accompanying drawings.

[0018] The template matching method of the present invention is used for text recognition processing, and its specific implementation steps are as follows:

[0019] S1: Image preprocessing process:

[0020] S1-1: Input the image to be recognized. The image to be recognized may be collected by an online camera device, or may be a saved scene image. In this embodiment, the collected image samples are taken by a camera, and the image samples come from 13 different types of paper medical test sheets. For the same test sheet of the same category, different angles, distances and lighting will be selected when taking pictures to enrich the test sample library of the image to be recognized.

[0021] S1-2: Image tilt correction: first detect ...

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 discloses a template matching method for character recognition processing, which belongs to the technical field of pattern recognition and image processing. The present invention performs feature extraction after preprocessing the input template and the image to be recognized: the text area of ​​the image is taken as a unit of adjacent connected domains, and the rectangular frame is calibrated to obtain a plurality of feature rectangles; then the current template image and the image to be recognized are Recognize the image for multiple coordinate origin normalization processing and scale normalization processing, and calculate the feature set similarity of each normalization process separately, and take the largest of all feature set similarities as the matching similarity of the current template image , and finally take the maximum matching similarity among all template images as the optimal matching template of the current image to be recognized. The invention is used for character recognition processing, especially a character recognition module of a medical test sheet recognition system, which solves the influence of factors such as scene image folds, scale changes, and illumination changes on character recognition, and improves the character recognition rate.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and image processing, and in particular relates to a template matching technology in character recognition technology. Background technique [0002] With the advancement of information technology, especially the rapid development of artificial intelligence technology, OCR (Optical Character Recognition) technology has achieved many achievements in the field of information recognition, and has also entered the practical stage of socialization. OCR technology has been successfully applied to all walks of life in society. In various industries, it is also widely used in the medical industry. [0003] From the point of view of statistical pattern recognition, character recognition is actually a pattern classification problem. Scholars at home and abroad have proposed many different recognition schemes, which can be roughly divided into classifier-based recognition methods and template-mat...

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 Patents(China)
IPC IPC(8): G06K9/62G06K9/32G06K9/36G06K9/40G06K9/20
CPCG06V10/22G06V10/243G06V10/20G06V10/30G06V30/10G06F18/22G06F18/24
Inventor 梅亚敏于鸿洋张平曾创
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com