The ability to employ neural networks to the task of image compression has been pointed out in research. The pre-dominant approach to image compression is centered around the backpropagation algorithm used to train on overlapping frames of the original picture. Several deficiencies can be identified with this approach. First, no potential time bounds are provided for compressing images. Second, utilizing backpropagation is difficult due to its computational complexity. To overcome these shortcomings we propose a different approach by concentrating on a general class of 3-layer neural networks of 2(N+1) hidden units. It is shown that the class /spl Nscr/* can uniquely represent a large number of images, in fact, the growth of this class is larger than exponential. Instead of training a network, it is automatically constructed. The obtainable compression rates (lossless) exceed 97% for square images of size 256/spl times/256 pixels.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Applying constructed neural networks to lossless image compression


    Contributors:


    Publication date :

    1994-01-01


    Size :

    432726 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Applying Constructed Neural Networks to Lossless Image Compression

    Romaniuk, S. G. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Fast lossless image compression

    Wehnes, J.C. / Hung-Ta Pai / Bovik, A.C. | IEEE | 1996


    Fast Lossless Image Compression

    Wehnes, J. C. / Pai, H.-T. / Bovik, A. C. et al. | British Library Conference Proceedings | 1996


    Near-lossless image compression techniques

    Ansari, R. / Memon, N. / Ceran, E. | British Library Online Contents | 1998


    Lossless and Near-Lossless Image Compression Based on Multiresolution analysis

    Arandiga, F. | British Library Conference Proceedings | 2005