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

Congealing Method Based on Fuzzy Entropy to Construct Chinese Characters and Recognition Method

A technology of Chinese characters and fuzzy entropy, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem that handwritten Chinese characters cannot be well represented, and achieve a good character recognition rate

Inactive Publication Date: 2017-06-06
高邮市好搜科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to avoid the deficiencies of the prior art, the present invention proposes a method for constructing Chinese characters and recognition based on the Congealing method of fuzzy entropy, overcoming the problem that handwritten Chinese characters cannot be well represented due to feature extraction

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
  • Congealing Method Based on Fuzzy Entropy to Construct Chinese Characters and Recognition Method
  • Congealing Method Based on Fuzzy Entropy to Construct Chinese Characters and Recognition Method
  • Congealing Method Based on Fuzzy Entropy to Construct Chinese Characters and Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0040] Construct Chinese characters in the training phase: train each Chinese character separately. In a certain character class, N images are randomly selected as training samples, and these N images are input into the Congealing algorithm based on fuzzy entropy for K iterations.

[0041] Specific steps are as follows:

[0042] (1) Initialize a transformation parameter vector for each of the N training images

[0043] v j =(t x ,t y ,θ,s x ,s y ,h x ,h y)=0(j=1toN), then the corresponding transformation matrix U is calculated respectively by formula (4) j .

[0044]

[0045] (2) Calculate the fuzzy entropy of the training character image.

[0046] A. There are N images in the image stack IS, and each image has M pixels. Represents the value of a pixel in the image stack, where i∈[1,M], j∈[1,N]. x i represents a pixel stack Each image I ∈ IS i...

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 relates to a Chinese character construction and recognition method based on the fuzzy entropy Congealing method. The image correction technology-Congealing method is applied to the issue of handwritten Chinese character recognition for the first time, the handwritten Chinese character recognition method based on the fuzzy entropy Congealing algorithm is put forward, and a high character recognition rate can be obtained through the method. The full-data-driven method is applied to the process of handwritten Chinese character recognition, and it is proven that the high recognition rate can be obtained.

Description

technical field [0001] The invention belongs to computer image processing, and relates to a method for constructing and recognizing Chinese characters, in particular to a method for constructing and recognizing Chinese characters based on a Congealing method based on fuzzy entropy. Background technique [0002] Handwritten Chinese character recognition methods have been widely studied in the field of machine learning and artificial intelligence. At present, handwritten Chinese character recognition methods are divided into online recognition and offline recognition. Among them, the research object of the offline recognition method is the separated and isolated handwritten Chinese character image, and the machine learning technology is used to classify the handwritten Chinese characters to be recognized into the correct category through the training and classification process. [0003] Due to the huge number of Chinese characters, various Chinese character structures, and di...

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): G06K9/68
Inventor 李映李方轶
Owner 高邮市好搜科技有限公司