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

An offline handwritten Chinese character recognition method based on dual-tree complex wavelet transform

A double-tree complex wavelet and Chinese character technology, applied in the field of Chinese character recognition, to achieve the effect of improving cognitive accuracy

Inactive Publication Date: 2019-03-08
HEFEI UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the defects of the existing Chinese character recognition technology, the present invention proposes an off-line handwritten Chinese character recognition method based on dual-tree complex wavelet transform, in order to solve the existing open-loop off-line handwritten Chinese character recognition model when faced with different objects. The same cognitive needs characterize the problem of the feature space of the object to be recognized, so that it can imitate the cognitive characteristics of human beings to adaptively adjust the feature space when facing different cognitive needs, and improve the accuracy of the offline handwritten Chinese character recognition system

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
  • An offline handwritten Chinese character recognition method based on dual-tree complex wavelet transform
  • An offline handwritten Chinese character recognition method based on dual-tree complex wavelet transform
  • An offline handwritten Chinese character recognition method based on dual-tree complex wavelet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In the present embodiment, a kind of off-line handwritten Chinese character cognition method based on dual-tree complex wavelet transform is carried out according to the following steps:

[0050] Step 1. Analysis of cognitive needs of off-line handwritten Chinese character strokes

[0051] Step 1.1, such as Figure 4 As shown, the Chinese characters "Cu, Chu, Chuan, Chuan, Chuan, Chuan, Building, Bed, Chuang, Chun" in the GB23122-80 standard simplified Chinese character library were selected for experimental research, and 15 characters with different writing styles were selected for each Chinese character. samples of handwritten Chinese characters, a total of 150 samples of handwritten Chinese characters; each Chinese character is selected by random sampling method, and 10 Chinese characters (total of 100 Chinese characters) in each Chinese character sample set are selected as training samples, and the remaining 5 Chinese characters (total of 50 Chinese characters) as ...

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 an off-line handwritten Chinese character cognition method based on double-tree complex wavelet transform, which is characterized in that it is carried out according to the following steps: the first step is to analyze the cognition requirements of off-line handwritten Chinese character strokes; the second step is to construct an off-line handwritten Chinese character recognition method; The initial feature model of mobile handwritten Chinese characters; the third step is to construct the candidate subspace of offline handwritten Chinese characters; the fourth step is to design the integrated classifier model of offline handwritten Chinese characters; the fifth step is to recognize the samples of offline handwritten Chinese characters The results are evaluated and the unrecognized off-line handwritten Chinese characters are repeatedly recognized according to the evaluation results. The invention constructs an optimized cognitive model of a specific test sample in the feedback iteration, solves the defect of the fixed cognitive model of an open-loop non-feedback off-line handwritten Chinese character recognition system, and improves the cognitive accuracy of the off-line handwritten Chinese character recognition system.

Description

technical field [0001] The invention belongs to the technical field of Chinese character recognition, and in particular relates to an off-line handwritten Chinese character recognition method based on double-tree complex wavelet transform. Background technique [0002] Chinese character recognition is an important research field of pattern recognition, and it has a wide range of applications in technical fields such as office and teaching automation, automatic recognition of bank notes, and language and text information processing. At present, the research on the feature extraction method of Chinese characters includes academic papers that have made in-depth theoretical analysis, and engineering methods for practical application, such as the invention patent "Chinese Character Recognition Method and Device" (CN102867178A) and the invention patent "Based on Identification and Return Yihua's Handwritten Chinese Character Recognition Method" (CN102831434A). [0003] Chinese In...

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): G06K9/52G06K9/62
CPCG06V10/52G06V30/287G06F18/241
Inventor 李帷韬王光新宋程楠陈克琼王建平
Owner HEFEI UNIV OF TECH
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