Neural network model for compressing/decompressing image/acoustic data files

Abstract

A new neural model for direct classification, DC, is introduced for acoustic/pictorial data compression. It is based on the Adaptive Resonance Theorem and Kohonen Self Organizing Feature Map neural models. In the adaptive training of the DC model, an input data file is vectorized into a domain of same size vector subunits. The result of the training (step 10 to 34) is to cluster the input vector domain into classes of similar subunits, and develop a center of mass called a centroid for each class to be stored in a codebook (CB) table. In the compression process, which is parallel to the training (step 33), for each input subunit, we obtain the index of the closest centroid in the CB. All indices and the CB will form the compressed file, CF. In the decompression phase (steps 42 to 52), for each index in the CF, a lookup process is performed into the CB to obtain the centroid representative of the original subunit. The obtained centroid is placed in the decompressed file. The compression is realized because the size of the input subunit ((8 or 24)*n2 bits) is an order of magnitude larger than its encoding index log2 [size of CB] bits. In order to achieve a better compression ratio, LZW is performed on CF (step 38) before storing (or transmitting) it.

Dependencies are inferred from the claim text.