In this work, a subband domain textual image compression method is develope
d. The document image is first decomposed into subimages using binary subba
nd decompositions. Next, the character locations in the subbands and the sy
mbol library consisting of the character images are encoded, The method is
suitable for keyword search in the compressed data. It is observed that ver
y high compression ratios are obtained with this method. Simulation studies
are presented.