Image compression forms the backbone for several applications such as storage of images in a database, picture archiving, TV and facsimile transmission, and video conferencing. Compression of images involves taking advantage of the redundancy in data present within an image. A fundamental goal of image compression is to reduce the bit rate for transmission and storage while maintaining an acceptable fidelity or image quality. Existing VQ algorithms however, suffer from a number of practical problems e.g. codebook initialization, long search process, and getting trapped in local minima. This paper presents an adaptive vector quantization algorithm which uses a neuro-fuzzy clustering technique for optimizing the distortion measure. The fuzzy approach forms the basis for accurately optimizing each codevector by determining the fuzzy centroid of each class. In addition, a multiresolution wavelet decomposition scheme is adopted to make the image better suited for compression and to enable its progressive transmission.
|Number of pages||6|
|State||Published - 1996|
|Event||Proceedings of the 1996 IEEE Southwest Symposium on Image Analysis and Interpretation - San Antonio, TX, USA|
Duration: Apr 8 1996 → Apr 9 1996
|Conference||Proceedings of the 1996 IEEE Southwest Symposium on Image Analysis and Interpretation|
|City||San Antonio, TX, USA|
|Period||04/8/96 → 04/9/96|