IMAGE SIGNAL COMPRESSING METHOD BY VECTOR QUANTIZATION

A method of compressing image signals by vector quantization comprises the steps of dividing two-dimensional image signals into blocks B each comprising the signals at adjacent picture elements, selecting a vector that corresponds with the minimum distortion to differences between the image signals in each block B and a representative value m of signals or interpolation-predicted values for the image signals, and encoding the information representing the selected vector, and the information representing the representative value m or the information utilized for calculating the interpolation-predicted values. The two-dimensional image signals are divided into blocks B' deviated from the blocks B. For each of partial regions of the block B overlapping the blocks B', a representative value n calculated for the block B' including the partial region is used as the representative value m for the partial region. Or, the interpolation-predicted values in the block B are predicted based on the representative values n in all of the blocks B' partially overlapping the block B.