The Recognition of CAPTCHA

Abstract

CAPTCHA is a completely automated program designed to distinguish whether the user is a computer or human. As the problems of Internet security are worsening, it is of great significance to do research on CAPTCHA. This article starts from the recognition of CAPTCHAs, then analyses the weaknesses in its design and gives corresponding recognition proposals according to various weaknesses, finally offers suggestions related to the improvement of CAPTCHAs. Firstly, this article briefly introduces the basic steps during the decoding process and their principles. And during each step we choose methods which are better adapted to the features of different CAPTCHA images. Methods chosen are as followings: bimodal method in binarization, improved corrosion algorithm in denoising, projection segmentation method in denoised image processing and SVM in recognition. Then, we demonstrate detailed process through the samples taken from the online registration system of ICBC, show the recognition effect and correct the results according to the statistical data in the process. This article decodes CAPTCHAS from three other large banks in the same way but just provides the recognition results. Finally, this article offers targeted suggestions to the four banks based on the recognition effect and analysis process stated above.

CAPTCHA – Security affecting User Experience

“…In Figure 6, an example of a game can be seen, where the user needs to drag the food to the baby's mouth. Many studies have been conducted on CAPTCHA tests, some focusing on the security analysis (Azad, 2013;Tayade & Bartere, 2015;Wang, Zhang, Jiang, & Song, 2014), others on differences between types of tests (Bhalani, & Mishra, 2015;Foley, 2012;Singh & Pal, 2014;Veesam & Babu, 2015), and others examined the combination between security and user friendliness (Gossweiler, Kamvar, & Baluja, 2009). Few focused on the user experience and their opinion on CAPTCHA tests (Fidas, Voyiatzis, & Avouris, 2011;Tangmanee & Sujarit-apirak, 2013).…”

A Recognition Method of CAPTCHA with Adhesion Character

“…However, now there are a lot of noise interference in the CAPTCHA and it is not ideal to use OCR to extract characters directly.WANG et al used the SVM training to recognize the image and compare it with the OCR directly. The experiments show that SVM training has better recognition effect [10].…”

Automated CAPTCHA Solving: An Empirical Comparison of Selected Techniques

“…A popular strategy in the research literature is the one followed by [19,20,21,14,18], where authors attempt to solve specific text-based challenges by introducing a combination of techniques for the transformation of the image, character extraction and recognition for each deployed CAPTCHA scheme. Besides the noise removal and segmentation techniques, which are depended on the text-based challenge, the main difference between the aforementioned strategies is the classification method being used.…”

“…Besides the noise removal and segmentation techniques, which are depended on the text-based challenge, the main difference between the aforementioned strategies is the classification method being used. In [19,20,21], authors create a custom recognizer with the use of Support Vector Machine (SVM). In [14,18] an already existing OCR engine is being used instead.…”