Efficient coding by neuro-fuzzy clustering in vector quantization of wavelet decomposed signals

Multiresolution representation of wavelets in image decomposition and coding shows potential of developing an efficient image compression technique with minimum distortion when vector quantization (VQ) is used. This paper presents a multiresolution and adaptive approach to VQ codebook generation by employing a fuzzy distortion measure embedded in a self-organizing neural network ensuring fast convergence and minimum distortion. Multiresolution codebooks are generated for the wavelet decomposed images using neuro-fuzzy clustering algorithms resulting in significant improvement in the coding process. The signal transformation and vector quantization stages together yield at least, 64:1 bit rate reduction with good visual quality and acceptable peak signal to noise ratio and mean square error. The performance of this new VQ coding technique has been compared to that of the well-known Linde, Buzo, and Gray-VQ for a variety of image classes. In each case, the new VQ technique demonstrated superior ability for fast convergence with minimum distortion at similar bit rate reduction than the existing VQ techniques