Image compression using artificial neural network

Image compression is essential where images need to be stored, transmitted or viewed quickly and efficiently. The artificial neural network is a recent tool in image compression as it processes the data in parallel and hence requires less time and is superior over any other technique. The reason that encourage researchers to use artificial neural networks as an image compression approach are adaptive learning, self-organization, noise suppression, fault tolerance and optimized approximations. A survey about different methods used for compression had been done. From the above study, multilayer feed forward network has been used due to its efficiency. The choice of suitable learning algorithm is application dependent. A new approach by modifying the training algorithm to improve the compression is proposed here. Protection of image contents is equally important as compression in order to maintain the privacy. So authentication and protection can be incorporated into the proposed system in future.