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

Hollow verification code quick identification method

An identification method and verification code technology, applied in the field of verification code identification

Active Publication Date: 2020-05-05
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing verification code recognition methods are suitable for solid verification codes, and the few recognition methods for hollow verification codes have room for improvement in recognition accuracy and recognition speed.

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
  • Hollow verification code quick identification method
  • Hollow verification code quick identification method
  • Hollow verification code quick identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0043] Embodiment two, see figure 2 As shown, a fast recognition method for hollow captcha consists of five stages: preprocessing, filling, segmentation, merging and recognition:

[0044] Preprocessing: convert the verification code image into a binary image, and then refine and repair the character outline.

[0045] Filling: First, mark all connected regions; then, use the inner and outer contour algorithm to find the noise block; next, mark the noise block as the background; finally, fill the non-background area to get a solid string.

[0046]Segmentation: Using the different connected region labels obtained in the filling stage, the solid string is segmented into most single characters and few character components.

[0047] Merging: The character components obtained in the segmentation stage are merged into a single character using the least nearest neighbor algorithm.

[0048] Recognition: Use Convolutional Neural Networks for Recognition.

[0049] The following five s...

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 present invention belongs to the technical field of verification code identification, and in particular relates to a method for quickly identifying a hollow verification code. Fill the character blocks to obtain solid characters; then, split to obtain individual characters and character components; then, analyze the structural characteristics and order associations of character components, and use the minimum neighbor algorithm to merge to obtain a single character without redundancy; finally, use volume The product neural network recognizes the individual characters obtained after segmentation and merging, and obtains the final cracking result. Compared with the existing recognition methods, the present invention not only keeps the original structure from being damaged, but also guarantees accurate repair of broken parts of character outlines, can reduce filling time, improve filling accuracy, and realize accurate acquisition and rapid identification of hollow verification codes , the recognition success rate is greatly improved, the applicability is strong, and it has good application value.

Description

technical field [0001] The invention belongs to the technical field of verification code identification, and in particular relates to a method for quickly identifying hollow verification codes. Background technique [0002] With the rapid development and popularization of the Internet, various network services provide great convenience for people's life, such as e-commerce, online teaching, e-mail, social networking and so on. However, malicious software will actively attack these services, including batch registration, machine posting, mass spam, large-scale ticket swiping, etc. In order to fight against it, CAPTCHA (Completely Automated Public Turing Test to tell Computers and Human Apart) came into being. It is a public automatic program that distinguishes whether the user is a human or a computer, also known as HIP (Human Interactive Proofs) or captcha technology. As a mechanism to strengthen network security verification, it has been widely used in various network ser...

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): G06K9/32G06K9/34G06K9/38G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/62G06V30/153G06V10/267G06V10/28G06V30/10G06N3/045G06F18/24147
Inventor 罗向阳陈俊张祎王平巩道福杨春芳刘粉林王道顺
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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