Digital Image Compression Using Neural Networks

Compression of data in any form is a large and active field as well as a big business. Image compression is a subset of this huge field of data compression, where we undertake the compression of image data specifically. Research in this field aims at reducing the number of bits needed to represent an image. Inter-pixel relationship is highly non-linear and unpredictive in the absence of a prior knowledge of the image itself. Thus artificial neural networks has been used here for image compression by training the net using the image to be compressed. The ANN takes into account the psycho visual features, dependent mostly on the information contained in images. The algorithms, on application on the image data preserves most of the characteristics of the data while working in a lossy manner and maximize the compression performance. The results have been checked with and without the use of quantization, and without median filtering of the image. The ANN algorithm used here is mainly the back-propagation of multilayer perceptrons.