A method and device for realizing slider verification code identification

Abstract

The embodiment of the invention discloses a method and a device for realizing sliding block verification code identification, and the method specifically comprises the steps: obtaining an original image comprising a sliding block region of a sliding block verification code and a sliding block missing region of the sliding block verification code, and determining candidate target points according to the color depth difference between pixel points in the original image. And screening out a target angular point of the to-be-identified area from the candidate target points, namely determining thetarget angular point of the sliding block area and the target angular point of the sliding block missing area. And if yes, determining the position of the sliding block region according to the targetangular point of the sliding block region and determining the position of the sliding block missing region according to the target angular point of the sliding block missing region to complete identification of the sliding block verification code. Visibly, according to the scheme provided by the invention, the target angular point of the to-be-identified area can be finally determined by calculating the color depth difference characteristics of the pixel points in the original image, so that the sliding block verification code is identified, identification does not need to be carried out through a deep learning model, the identification calculation amount is reduced, and the identification speed is increased.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to a method and device for realizing identification of a slider verification code. Background technique [0002] In recent years, many Internet application systems have used verification code technology to prevent robot programs from accessing. Among them, the slider verification code has been widely used because of its simple operation, good user experience, and strong security. However, in some scenarios, such as automated testing, it is necessary to automatically identify the verification code. [0003] In the prior art, a neural network-based machine learning algorithm is usually used to identify the slider verification code. The specific implementation process includes: marking the position of the slider and the position of the slider gap in the training image including the slider verification code, using A large number of marked training images are trained to g...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides a method and device for realizing the recognition of the slider verification code, so as to solve the technical problems of realizing the recognition of the slider verification code in the prior art with a large amount of calculation and a slow recognition speed

Images