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

A Binarization and Segmentation Method for Chinese Character Captcha

A Chinese character and verification code technology, applied in character and pattern recognition, character recognition, instruments, etc., to achieve accurate character segmentation results and strong tolerance

Active Publication Date: 2021-01-12
SHANGHAI UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is not suitable for splitting Chinese character verification codes. In Chinese characters, a character may contain multiple connected domains.

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 Binarization and Segmentation Method for Chinese Character Captcha
  • A Binarization and Segmentation Method for Chinese Character Captcha
  • A Binarization and Segmentation Method for Chinese Character Captcha

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0025] Such as figure 1 As shown, a binarization and segmentation method for Chinese character verification codes, the specific operation steps are as follows:

[0026] (1) Grayscale the obtained original verification code image, and linearly map the pixel values ​​of the image to the [0,1] interval.

[0027] (2) Denoise and binarize the grayscale image. If there are many or thick interference lines in the image, or there is a gradient background, perform morphological reconstruction without Gaussian smoothing and morphological reconstruction with Gaussian smoothing on the image, and then perform a pixel-by-pixel OR operation on the two reconstruction results , to get the denoised image. Among them, the kernel size of Gaussian smoothing is 1.0. If the contrast between the characters in the image and the background color is not strong, th...

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 binarization and segmentation method for Chinese character verification codes, aiming at effectively segmenting the foreground and background of Chinese character images. This method mainly uses Gaussian smoothing filter, morphological reconstruction and Mean Shift clustering method. First, the image is grayscaled and denoised. The obtained verification code image is grayscaled, and different denoising methods are applied to the image noise to obtain a character image suitable for character recognition. Secondly, binarize the image to separate the foreground character from the background, and then locate the pixel representing the character. Again, cluster the character points. Apply the Mean Shift clustering method to the character pixels in the original image to obtain the clustering of these characters. After cluster adjustment, character pixels at the same cluster point will be regarded as representing the same character. Thus, the pixel point representation of each character in the verification code image is obtained, that is, the character segmentation is completed.

Description

technical field [0001] The invention relates to a method for filtering background noise in two-dimensional character verification codes, more specifically, a binarization and segmentation method for Chinese character verification codes. Background technique [0002] Character verification codes are widely used in Internet services as a tool to determine whether network requests come from legitimate users, so as to prevent a large number of automatic requests from machines and ensure the stable operation of website servers. Character verification codes are currently the most commonly used type of verification codes. This type of verification code usually requires the user to complete a character recognition task, and the user needs to correctly identify each character in the character image generated by computer image technology to pass the verification. In order to increase the difficulty of machine recognition of verification codes, the images of such verification codes ar...

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): G06K9/34G06K9/54G06K9/62
CPCG06V30/153G06V10/20G06V30/10G06F18/23
Inventor 武星裴孟齐
Owner SHANGHAI UNIV
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