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

Text verification code recognition method and device based on cross-domain element learning and storage medium

A recognition method and meta-learning technology, applied in the fields of computer vision and image processing, can solve problems such as poor cross-domain effects of meta-learning algorithms and unbalanced data

Active Publication Date: 2021-07-20
HARBIN INST OF TECH AT WEIHAI
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This method combines the idea of ​​small sample learning with the joint training method of multi-source domain data to solve the problems of poor cross-domain effect of meta-learning algorithm and unbalanced data in the process of character 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
  • Text verification code recognition method and device based on cross-domain element learning and storage medium
  • Text verification code recognition method and device based on cross-domain element learning and storage medium
  • Text verification code recognition method and device based on cross-domain element learning and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] A text verification code recognition method based on meta-learning, such as figure 1 shown, including the following steps:

[0083] (1) Meta-training stage

[0084] First, generate a large number of verification code pictures with different security features as basic training data through the verification code generator;

[0085] Then, use contour detection to segment the verification code pictures with different security features in the basic training data, and input the segmented characters into the ResNet neural network model for feature extraction;

[0086] Finally, the loss value of the estimated category is obtained;

[0087] (2) Fine-tuning stage

[0088] Label a small number of verification code pictures different from the basic training data in the meta-training stage, fine-tune the ResNet neural network model, and obtain the final recognition result.

Embodiment 2

[0090] According to the meta-learning-based text verification code recognition method described in Embodiment 1,

[0091] In the cross-domain meta-learning task, the source domain data, that is, the basic training data, is denoted as (x s ,y s ), where x s Indicates the source domain data sample, y s Indicates the label corresponding to the source domain data sample, and the target domain data is a small number of verification code pictures of different types from the basic training data, expressed as (x t ,y t ), where x t Indicates the target domain data sample, y t Indicates the label corresponding to the target domain data sample, and there is a difference between the source domain data and the target domain data in one or more items in the feature space, category space or marginal distribution. Such as figure 1 As shown, the verification code in the source domain data and the verification code in the target domain data contain different fonts, colors, background in...

Embodiment 3

[0136] A computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the text verification code recognition method based on cross-domain meta-learning described in Embodiment 1 or 2 are realized.

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 text verification code recognition method and device based on cross-domain element learning and a storage medium. The method comprises the steps of (1) an element training stage: firstly, generating a large number of verification code pictures with different security features as basic training data; then, carrying out character segmentation, and inputting segmented characters into the ResNet neural network model for feature extraction; and finally, obtaining a loss value of the pre-estimated category; and (2) a fine tuning stage: marking a small number of verification code pictures of different types from the basic training data in the meta-training stage, and performing fine tuning on the ResNet neural network model to obtain a final recognition result. The method has the characteristics of extremely small marked sample size, high model training speed, strong generalization ability and high recognition accuracy, solves the problems that an existing verification code recognition method needs a large amount of labeled data and the model migration difficulty is large, can meet the industrial requirements, and has wide application prospects.

Description

technical field [0001] The invention relates to a text verification code recognition method, device and storage medium based on cross-domain meta-learning, and belongs to the technical fields of computer vision and image processing. Background technique [0002] Captcha, also known as the anti-Turing test, is an automated mechanism for distinguishing between humans and computers. At present, verification codes are widely used by major commercial websites to prevent malicious cracking of passwords, swiping tickets, flooding and hacker attacks, etc., so as to ensure the information security of the websites. Although many new types of verification codes have been proposed in recent years, text verification codes are still one of the most widely used types of verification codes. Therefore, research on text verification codes will help to design a more secure and effective human-machine discrimination mechanism, thereby Promote the development of the field of information securit...

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
IPC IPC(8): G06K9/20G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/22G06V10/267G06V10/40G06N3/045G06F18/2415
Inventor 王瑶王佰玲王巍刘扬金楚浩
Owner HARBIN INST OF TECH AT WEIHAI
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