DETECTING THE WATERMARKED IMAGE IN VISUAL CAPTCHA FORMAT AND GETTING ITS ENCRYPTED INFORMATION

摘要

In this paper a plan is suggested that is a combination of CAPTCHA security codes and WATERMARKING studies. With an increasing number of automated software bots and automated scripts that exploit public web services, the user is commonly required to solve a Turing test problem, namely a Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), before they are allowed to use web services. The purpose of CAPTCHA is to block form submissions from spam bots - automated scripts that harvest email address from publicly available web forms. Programmers have worked to create special algorithms that can read the distorted letters from images with the purpose of defeating CAPTCHA images. Strong CAPTCHA must be used to insure that spam bots will not pass and submit their information to forms. On the other hands, CAPTCHA stands for "completely automated public Turing test to tell computers and humans apart. Watermarking and fingerprinting are part of the STEGANOGRAPHY." A watermark is an image which appears on fine papers or on some documents to prevent counterfeiting. The watermark is designed to appear only when the paper is held at a particular angle, or against a black background. Standard paper usually does not include a watermark, as making a watermark will drive the cost of the paper up. Fine art papers use watermarks to identify the manufacturer, and companies such as banks frequently use specially watermarked paper for security. In this proposed topic we want to watermark an encryption information in the arbitrary image, then distort this image (by changing the location of components of image) and send it to the desired receiver. In the destination, receiver gets the image and he/she must detect the correct image and after that he/she can access to its information that is embedded on it. More details have been explained in the next section.