METHOD FOR COMPRESSING IMAGE SIGNALS

Wavelet transformation is carried out on an original image signal, and the original image signal is thereby decomposed into image signals, each being of one of a plurality of different frequency bands. The degree of importance of each of different portions of the image is then determined from one of the image signals or from the original image signal. Labeling processing is carried out on the image signal, from which the degree of importance of each of different portions of the image was determined, in accordance with the determined degree of importance of each of different portions of the image. The image signals are quantized in accordance with the results of the labeling processing such that a larger number of bits may be allocated to each of picture elements in a portion of the image determined as having a higher degree of importance. The quantized image signals are then encoded. The original image signal is thus compressed with a high compressibility such that the image quality of the important portion of the original image may not be lost.