Depth learning method and device for character verification code recognition

A deep learning and verification code technology, applied in the field of character recognition, can solve the problems of inability to segment two single characters well, lose context information, and be difficult to satisfy, and achieve powerful feature extraction function and classifier performance. The effect of improving and improving the speed of recognition

Inactive Publication Date: 2017-08-22
SHENZHEN IPIN INFORMATION TECH CO LTD
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If a simple vertical projection segmentation algorithm is used, the two cohesive single characters cannot be segmented well, and other methods based on segmentation points are complicated and the effect is not satisfactory
In addition, the recognition of the verification code is divided into independent single characters for recognition. In the verification code recognition with semantics such as Chinese idioms, the context information will be lost.
These shortcomings will greatly affect the final recognition effect.

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
  • Depth learning method and device for character verification code recognition
  • Depth learning method and device for character verification code recognition
  • Depth learning method and device for character verification code recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0045] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways than described here. Therefore, the protection scope of the present invention is not limited by the specific implementation disclosed below. Example limitations.

[0046] figure 1 A flowchart showing a deep learning method for character verification code recognition according to the present invention.

[0047] Such as figure 1 As shown, the deep learning method of a ...

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 depth learning method for character verification code recognition. The method comprises the steps that 1 a model is trained through a data training set with a label tag; and 2 the trained model is used to predict a character in a new verification code picture. According to the invention, a general verification code recognition system method is realized; after a new website verification code is encountered, a high accuracy recognizer is acquired by training the model or fine-tuning the trained model; the verification code impediment of a website is broken; the model provided by the invention is simple to construct; and the accuracy of verification code recognition is improved.

Description

technical field [0001] The present invention relates to a character recognition method, and more specifically, to a deep learning method and device for character verification code recognition. Background technique [0002] Verification code (CAPTCHA) is a reverse Turing test technology, which is often used on websites to distinguish between human users and computer programs, to prevent password cracking, swiping tickets, or malicious behavior such as flooding forums, which can effectively ensure the safety and normality of websites run. The design of the verification code is based on the fact that it is extremely easy for humans to recognize objects and characters, but it is very difficult for computers. Identification of verification codes is an important research topic in the field of artificial intelligence. Studying the cracking method of the verification code can be used to detect the safety of the verification code, and it can also be a great reference for website ve...

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): G06K9/62G06K9/20
CPCG06V10/22G06F18/214
Inventor 张小彬潘嵘费行健
Owner SHENZHEN IPIN INFORMATION TECH 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap