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

Verification code identification method and system based on deep learning

A technology of deep learning and recognition method, which is applied in the field of verification code recognition method and system based on deep learning, which can solve problems such as inability to handle verification codes, and achieve the effect of fast recognition speed, less complexity and high accuracy

Pending Publication Date: 2019-06-25
浪潮卓数大数据产业发展有限公司
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this technical solution cannot handle the verification codes encountered in the process of web crawlers, realize automatic identification of verification codes, and 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 deep learning
  • Verification code identification method and system based on deep learning
  • Verification code identification method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] as attached figure 1 As shown, the verification code recognition method and system based on deep learning of the present invention, the steps of the method are as follows:

[0067] S1. Image collection and labeling: Use crawlers to crawl the verification code pictures of the website into 500 test sets and 400 training sets, and manually label them; among them, the text in the verification code pictures is composed of 10 numbers and 52 Four of them are randomly selected from uppercase and lowercase letters;

[0068] S2. Image preprocessing: use the image processing tool CV2 to preprocess the verification code image; the specific steps are as follows:

[0069] S201. Grayscale processing: process the RGB three-channel original image of the verification code image into a single-channel image, as attached image 3 shown;

[0070] S202, binarization processing: set the pixel threshold to 180, set the pixel value greater than 180 to 255, and set the pixel value less than 80...

Embodiment 2

[0086] as attached Figure 5 As shown, the verification code recognition system based on deep learning of the present invention includes an image collection and labeling module, an image preprocessing module, a deep learning model building module, and a model training and verification module; wherein, the image collection and labeling module is used for Use a crawler to crawl the verification code pictures of the website into 500 test sets and 400 training sets, and manually label them; the image preprocessing module is used to preprocess the verification code pictures using the image processing tool CV2; the image preprocessing module It includes a grayscale processing module, a binarization processing module, a noise removal module, and a picture standardization module; among them, the grayscale processing module is used to process the original RGB three-channel image of the verification code image into a single-channel image; the binarization processing module It is used to...

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 a verification code identification method and system based on deep learning, and belongs to the field of computer vision and image processing. The technical problem to be solved by the invention is how to process the verification code encountered in the web crawler process. According to the technical scheme, the verification code identification method based on deep learningcomprises the following steps: S1, image collection and labeling: crawling verification code images of a website by using a crawler to divide the verification code images into a test set and a training set, and manually labeling; S2, image preprocessing: preprocessing the verification code image by using an image processing tool CV2; S3, building a deep learning model: building the deep learningmodel by using a deep learning framework keras, a development tool python and training set data; and S4, model training and verification. The verification code identification system based on deep learning comprises an image collection and labeling module, an image preprocessing module, a deep learning model building module and a model training and verification module.

Description

technical field [0001] The present invention relates to the fields of computer vision and image processing, in particular to a verification code recognition method and system based on deep learning. Background technique [0002] With the rapid development of Internet technology in recent years, network security has gradually entered the public's field of vision and has become a link that must be taken seriously. In order to prevent malicious batch registration of websites, anti-crawlers, etc., the use of verification codes has also become popular. Large website forums and websites that require input of verification codes can be seen everywhere. For the company's crawler project, research on captcha recognition technology is also on the agenda. Traditional verification code recognition uses OCR (optical identifier) ​​technology such as Google's open-source tesseract framework, but the requirements for verification codes are harsh and the accuracy rate is low; with the rise o...

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): G06F21/46G06K9/18G06K9/62G06N3/04G06N3/08G06V30/224
Inventor 王景玉
Owner 浪潮卓数大数据产业发展有限公司
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