RECONSTRUCTION OF HIDDEN IMAGES USING

This paper proposes a blind image separation method us­ ing wavelet transform and an entropy-maximiza tion algo­ rithm. Our blind separation algorithm is an improved version of the entropy-maximiza tion algorithms presented by Bell­ Sejnowsky and Amari. These algorithms work well for sig­ nals having a supergaussian distribution, such as speech and audio. The proposed method is to apply the improved algo­ rithm to the wavelet coefficients of a natural image, whose distribution is close to supergaussian. Our method success­ fully reconstruct twelve images hidden in another twelve im­ ages which are similar each other.