Handwritten numeral recognition method based on characteristic matrix similarity analysis

A similarity analysis and feature matrix technology, applied in character recognition, character and pattern recognition, instruments, etc., can solve the problems that the theory and learning algorithm need to be further improved, achieve fast speed, high processing efficiency, and ensure accuracy and precision Effect

Active Publication Date: 2017-10-24
ZHEJIANG UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the deep learning of neural networks requires a large number of sample support for training to obtain a better recognition function, and the theory and learning algorithms need to be further improved

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
  • Handwritten numeral recognition method based on characteristic matrix similarity analysis
  • Handwritten numeral recognition method based on characteristic matrix similarity analysis
  • Handwritten numeral recognition method based on characteristic matrix similarity analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to understand the purpose and process of the present invention more fully, the present invention will be described in detail below in conjunction with the accompanying drawings and specific examples, and the purpose and effect of the present invention will become more obvious.

[0042] A kind of handwritten digit recognition method based on feature matrix similarity analysis provided by the invention, the steps are as follows:

[0043] 1) Obtain the handwritten digital image to be recognized, and back up the original handwritten digital image so that the subsequent administrator can confirm whether the recognition result is correct or not;

[0044] 2) converting the obtained original handwritten digital image into a grayscale image;

[0045] 3) converting the obtained grayscale image into a binary image;

[0046] 4) smoothing, optimizing and cutting the obtained binary image, and then scaling to obtain the binary feature matrix of the image to be recognized; ...

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 handwritten numeral recognition method based on characteristic matrix similarity analysis. The method comprises the following steps: A, obtaining a to-be-recognized handwritten numeral image; B, converting the obtained original handwritten numeral image to a gray level image; C, converting the obtained gray level image to a binary image; D, performing smooth optimization, cutting, and zoom on the obtained binary image, to obtain a binary characteristic matrix of the to-be-recognized image; E, combining the obtained binary characteristic matrix with each standardized numerical characteristic matrix in pairs, to form characteristic matrix pairs, respectively performing similarity analysis; analyzing an obtained association coefficient result, the higher the association coefficient be, the higher the similarity be, and the standardized number corresponding to the characteristic matrix with the highest similarity being the number obtained by recognition. Through the method, a computer can accurately recognize handwritten numeral. Compared with the prior art, the method does not need large quantity of training samples to support a recognition technology, and training time is short, calculated amount is low, and recognition precision is high.

Description

technical field [0001] The invention relates to the fields of image processing and pattern recognition, in particular to a method for recognizing handwritten digits based on characteristic matrix similarity analysis. Background technique [0002] With the rapid development of information technology, there is a large amount of data to be input into the computer network. Therefore, how to replace manual input with efficient and intelligent recognition of handwritten numbers by machines has become an urgent problem to be solved. The advantages of machine intelligent recognition are that firstly, the recognition speed is greatly accelerated, secondly, various errors that may occur in manual input are avoided, and thirdly, the operation process of the entire system can be optimized. [0003] Handwritten digit recognition has always been a research hotspot in the field of image processing and pattern recognition. At present, handwritten digit recognition technology has been widely...

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): G06K9/00G06K9/62
CPCG06V30/36G06V30/10G06F18/22
Inventor 周若宸杨强
Owner ZHEJIANG UNIV
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