Comparison of prediction methods for differential image processing applications

An overview of ongoing research related to the development of an image data compression algorithm using artificial neural networks (ANNs) is presented. The data compression technique under study uses an ANN to perform vector quantization (VQ). A good predictor is one of the essential components of the image compression technique being explored. The performance of the various predictors are compared including an average predictor, a median predictor, a recurrent artificial neural network (RANN) predictor, and a second-order optimal linear predictor. It is shown that, for some cases, a relatively simple recurrent artificial neural network predictor performs close to the second-order optimal linear predictor and better than the average and the median predictors.<>