This paper presents a compression method for still images, based on Kohonen's neural network. To avoid the edge degradation caused by high compression ratio, the blocks are classified into two classes : blocks with high activity (edge blocks) and blocs with low activity. The image is divided first into blocks of 16 pixels. Each block of high activity are divided again into small blocks of 4 pixels. Blocks of high and low activity are coded separately with different codebooks. We have obtained a noticeable improvement of visual quality of all the rebuild images while keeping an important compression rate. This method has been tested on medical images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Medical images compression by neural networks


    Contributors:
    Benamrane, N. (author) / Daho, Z.B. (author) / Shen, J. (author)


    Publication date :

    2003-01-01


    Size :

    359973 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Medical Images Compression by Neural Networks

    Benamrane, N. / Daho, Z. B. / Shen, J. et al. | British Library Conference Proceedings | 2003


    Performance Comparison of Compression Schemes for Medical Images

    Karthik, S. / Shanmugavadivu, N. / Visual Information Engineering Network (Institution of Engineering and Technology) | British Library Conference Proceedings | 2006


    Hartley Transform in Compression of Medical Ultrasonic Images

    Duleba, I. / IEEE | British Library Conference Proceedings | 1999


    Image compression using principal component neural networks

    Costa, S. / Fiori, S. | British Library Online Contents | 2001


    Convolutional Neural Networks for Enhanced Compression Techniques

    Gnacek, Matthew / Heatwole, Cory / Fan, David et al. | IEEE | 2021