Verification code identification method and system based on target detection method

A target detection and recognition method technology, which is applied in the verification code recognition method and system field, can solve the problem of unable to slide the jigsaw verification code operation, etc., and achieve the effect of improving accuracy, reducing time cost, and improving accuracy

Inactive Publication Date: 2020-07-10
SICHUAN XW BANK CO LTD +1
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the sliding puzzle verification code cannot be operated in the prior art, the present invention provides a verification code recognition method and system based on a target detection method, the purpose of which is to prepare for data collection on major websites and realize Automatically identify sliding puzzle verification codes to improve the accuracy of verification code 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
  • Verification code identification method and system based on target detection method
  • Verification code identification method and system based on target detection method
  • Verification code identification method and system based on target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Please refer to figure 1 , a verification code recognition method and system based on a target detection method of the present invention, the steps of the method include:

[0041]A. Collect slider pictures of different shapes and create a slider picture data set, use the selenium library (a tool for web application testing, Selenium tests can be run directly in the browser) to manipulate the browser to perform web page request operations, and perform Simulate login, take screenshots of the captcha pictures with gaps, and extract the captcha pictures with gaps; you need to define the login function to perform web page request operations, and use the selenium (for picture screenshots) automated test library and Chromedriver application to test the target website Request, call the browser.send_keys() function to simulate login (the website does not need to simulate login, then it will not be used), and arrive at the verification code page; use the screenshot() function of ...

Embodiment 2

[0068] Please refer to Figure 4 . A verification code recognition system based on a target detection method, characterized in that it includes a picture collection module, a picture processing module, a picture matching module and a picture verification module;

[0069] Wherein, the picture collection module (which can be realized by using the existing technology) is used to take a screenshot of the slider picture and the picture of the verification code with a gap in the slider puzzle verification code on the webpage, and extract these two pictures;

[0070] The image processing module is used to convert the RGBA four-channel to the transparent channel of the slider image to obtain an opaque slider image, set the value of the RGB three-channel to 0, and the value of the transparent channel "A" to 220, and only keep the slider image For the edge part of the image with a gap, RGB three-channel to single-channel processing is performed on the verification code image with a gap...

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 verification code recognition method and system based on a target detection method, and the method comprises the steps: A, collecting sliding block pictures in different shapes, building a data set, controlling a browser to carry out the webpage request operation through a selenium library, carrying out the simulated login, and carrying out the screenshot of a verification code picture; B, carrying out RGBA four-channel-to-transparent-channel processing on the sliding block picture to obtain an opaque sliding block picture, and carrying out the grey processing on theverification code picture with the notch; C, matching the pictures through a function in OpenCV, and calculating coordinates of the opaque slider picture and the verification code picture with the gap to obtain the displacement of the slider picture; D, simulating a mouse through a selenium library, moving the sliding block picture according to a manual sliding rule from fast to slow, and analyzing the verification code. According to the invention, the early-stage preparation work for data collection of all large websites, the automatic identification of the sliding jigsaw puzzle verificationcode is achieved, and the accuracy of verification code identification is improved.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a verification code recognition method and system based on a target detection method. Background technique [0002] With the rapid development of the Internet in recent years, the importance of information security and network security has been raised to the national strategic level. In order to prevent private users and even large enterprises from arbitrarily crawling website data, transforming it into commercial use or even conducting illegal and criminal activities, the captcha method in the anti-crawler field is gradually becoming popular. [0003] The sliding puzzle verification code method is used by many large Internet companies. This kind of verification code breaks the shortcomings of previous text and / or alphabetic verification codes, making traditional crawler methods inoperable. [0004] The Chinese patent document with the application number 201...

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): G06K9/62G06K9/46G06F21/36
CPCG06F21/36G06F2221/2133G06V10/44G06F18/22
Inventor 刘奔常晋源何婧林昱郑乐翟恩荣
Owner SICHUAN XW BANK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products