Certain investigation on Captcha design based on splitting, rotating and grid’s usage in the images against OCR

摘要

Network security consists of the provisions and policies adopted by a network administrator. Network security prevents and monitors unauthorized access, misuse, modification, or denial of a computer network and network-accessible resources. A CAPTCHA is aprogram that generates and grades tests that are human solvable, but beyond the capabilities of current computer programs. This technology is now almost a standard security mechanism for addressing undesirable or malicious Internet bot programs and has found widespread application on numerous commercial web sites including Google, Yahoo, and Microsoft's MSN. It is widely accepted that a good CAPTCHA must be both robust and usable. The problem in existing system is that the CPU memory required to randomly generate CAPTCHA images is somewhat significant, and if CAPTCHA forms are being used on a lot of websites simultaneously this can reduce the performance of the web server. In order to provide effective CAPTCHA, A method used in CAPTCHA is implementing the images of words. This method is based on the weak points of Optical Character Recognition (OCR) programs. OCRs can recognize the high quality texts using the common formats and standards. It will be more secure to add noisy backgrounds, colors and increasing the level of distortion against character recognition programs. It is difficult for them to read low-quality text and the manuscripts