Verification code identification method based on window sliding and convolutional neural network

Abstract

The invention provides a verification code identification method based on window sliding and the convolutional neural network for traditional English letter+digit+Chinese character verification code pictures. According to the method, firstly, a small quantity of verification code pictures are acquired, after noise reduction, to-be-identified character sets of the verification codes are extracted,each character set is turned and distorted, and background noise is added to each character set; secondly, the convolutional neural network is then utilized for the character sets, and each characterset is trained to acquire a single character classifier; and lastly, after the to-be-identified verification code pictures are pre-processed, connected domain segmentation is carried out, for each connected domain, window sliding is carried out, the trained single character classifiers are utilized for classification, and the final identification result is acquired. The method is advantaged in that a problem of segmentation difficulty caused by overlapping of the verification codes and excessive random character jitter can be effectively solved, through the method of employing the small quantity of verification code pictures, extracting the character sets from the pictures and autonomously generating the correlation training sets, data acquisition and data marking cost is greatly reduced.

Description

technical field [0001] The invention relates to the research fields of computer vision and image processing, in particular to a verification code recognition method based on window sliding and convolutional neural network. Background technique [0002] Verification code, usually refers to a series of randomly generated numbers or symbols to generate a picture, add some interference to the picture, such as randomly draw a few straight lines, draw some points (to prevent OCR), and let the user identify the verification code information with naked eyes , enter the form to submit website verification, and a function can only be used after the verification is successful. Generally, the place where the user ID is registered and the major forums must enter the verification code. [0003] The reason why the verification code is set is mainly to automatically distinguish whether the current user is a computer or a human, so as to prevent malicious password cracking, swiping tickets,...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide a verification code recognition method based on window sliding and convolutional neural network, which can effectively solve the problem that it is difficult to cut due to overlapping verification codes and excessive random jitter of characters , which has the advantages of low labor cost, good recognition effect and low time complexity

Images