Variable bit rate block truncation coding for image compression using Hopfield neural networks

A Hopfield neural network based block truncation coding (BTC) technique is presented in this paper. For this scheme, BTC is formulated as the minimization of a cost function in which the bit map distributions for the blocks are explicitly included. It is explained that this cost function may also be interpreted as a measure of the block detail. Based on the observation of the final value of the cost function found by the Hopfield network, a block may be classified as a high detail block or a low detail block, which are coded differently, giving a different compression ratio for each type. It is shown that using this new technique, compression ratios up to 7:1 with good reconstructed image quality can be achieved. Experimental results are presented to demonstrate the effectiveness of this new scheme