A novel image authentication scheme based on hyper-chaotic cell neural network

This paper presents a new image authentication scheme based on cell neural network with hyper-chaos characteristics (HCCNN). In the scheme, the authentication code, which is used as secret key and the pixel values of image are used for the input of HCCNN. The secret information that HCCNN produces is transmitted to the receiving end through secret channel. The receiver can then use the received secret information to authenticate the suspect image by comparing the original authentication code with that calculated from the suspect image. Simulations show that the suggested image authentication algorithm has the advantages of large key space and high security, and moreover, it can detect and locate the position of any slightly tampered parts of a suspect image. (C) 2009 Elsevier Ltd. All rights reserved.