Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for recognizing handwritten characters

A technology for handwritten characters and recognition methods, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of feature loss and low classifier performance, achieve enhanced classification ability, improve recognition accuracy, and avoid loss. Effect

Inactive Publication Date: 2019-01-01
ENNEW DIGITAL TECH CO LTD
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above technical problems, the present invention provides a handwritten character recognition method and system to solve the problems of feature loss and low performance of classifiers in the existing convolutional neural network handwritten character recognition

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
  • Method and system for recognizing handwritten characters
  • Method and system for recognizing handwritten characters
  • Method and system for recognizing handwritten characters

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Refer to the attached figure 1 , the technical scheme realization process of the recognition method of handwritten character of the present invention is as follows:

[0040] S1. Input handwritten characters.

[0041] Specifically, the handwritten characters may be in image format.

[0042] S2. Extracting gradient features of input handwritten characters;

[0043] Specifically, an 8-direction Gradient (gradient feature) feature is taken as an example for illustration.

[0044] Extract the 8-direction Gradient feature (gradient feature) of the input handwritten character, the gradient operator adopts the Sobel operator (Sobel operator), and calculate the 8 gradient feature maps by blocks Should Piece of Average value, the average value of all blocks is concatenated into a feature vector, which is the Gradient gradient feature vector.

[0045] Specifically, first normalize the character image I to a scale size of 48*48, and extract the Gradient eight-direction gradi...

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 a handwritten character recognition method and a system. The method and the system adopt the feature extraction strategy of multi-feature fusion, extract the gradient feature, the Gabor feature and the convolution neural network feature of the input handwritten character to fuse them and fully extract the useful information of the character. At the same time, aiming at the problem that the classification performance of convolution neural network classification layer is general, Support vector machine classifier is used to serially connect the above three features, and then input the principal component analysis model for dimension reduction to obtain feature vectors, input support vector machine classifier to achieve character recognition, improve the classificationability and increase the accuracy of character extraction.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, more specifically, to a handwritten character recognition method and system in the field of artificial intelligence. Background technique [0002] Character recognition technology is an extremely important branch in the field of artificial intelligence. Character recognition, especially handwritten character recognition, has always been a hot and difficult point in the field of image recognition. [0003] The current handwritten character recognition methods are mainly divided into two categories. One is the traditional handwritten character recognition method. This type of method mainly preprocesses characters, separates individual characters, and then extracts the artificial features of individual characters, mainly structural features and statistical features. Structural features include stroke features, corner features, topological structures, etc. Statistical features Includ...

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): G06K9/68G06K9/62G06N3/04
CPCG06V30/2455G06N3/045G06F18/2411G06F18/253
Inventor 吴香莲
Owner ENNEW DIGITAL TECH CO LTD