An identification method and device for VAPTCHA (Variation Analysis based Public Turing Test to Tell Computers and Humans Apart) codes

Abstract

The embodiments of the invention provide an identification method and device for VAPTCHA codes. The method comprises the steps of identifying line segment trajectories in a VAPTCHA code image by using a Hough Transform method based on an open source computer vision library Open CV; according to the identified line segment trajectories in the VAPTCHA code image, acquiring coordinate information of each line segment trajectory of the VAPTCHA code; according to the coordinate information of each line segment trajectory of the VAPTCHA code, acquiring information of a start point, a sliding trajectory and an end point of sliding of the VAPTCHA code; according to the information of the start point, the sliding trajectory and the end point of sliding of the VAPTCHA code, simulating mousedown, mouse move and mouseup events to perform verification of the VAPTCHA code. According to the technical solution, automatic machine identification of VAPTCHA codes can be performed simply and accurately, so that automatic security tests can be performed on websites with log-in requiring VAPTCHA codes; the method can be used for detecting the risk-resisting capability of websites and optimizing websites.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a gesture verification code recognition method and device. Background technique [0002] Gesture verification code: verification code is a public automatic program to distinguish whether the user is a computer or a human, and is the most important means to distinguish between human and machine in network applications. At present, the verification codes mainly fall into the following categories: graphic verification codes, rotating verification codes, general knowledge quiz verification codes, touch verification codes, and slider verification codes. Gesture verification code is a new type of verification code with a simple interface, a good user experience, and less interference to users. [0003] Gesture verification codes are generally recognized and verified by humans, but when new gesture verification codes are introduced to the market, if they all need to be recogn...

AI Technical Summary

Problems solved by technology

OCR also obtains the details of the picture by analyzing the whole picture. The recognition process has to go through a series of complicated steps. In these steps, an error occurs in the previous step, which will directly affect the processing results of the subsequent steps.

[0006] To sum up, it can be seen that the machine automatic recognition of gesture verification codes in the prior art is relatively cumbersome and complicated

Images