Improving Karhunen-Loeve based transform coding by using square isometries

We propose, for an image compression system based on the Karhunen-Loeve transform implemented by neural networks, to take into consideration the 8 square isometries of an image block. The proper isometry applied puts the 8*8 square image block in a standard position, before applying the image block as input to the neural network architecture. The standard position is defined based on the variance of its four 4*4 sub-blocks (quadro partitioned) and brings the sub-block having the greatest variance in a specific corner and in another specific adjoining corner the sub-block having the second variance (if this is not possible the third is considered). The use of this “preprocessing” phase was expected to improve the learning and representation ability of the network and, therefore, to improve the compression results. Experimental results have proven that the expectations were fulfilled and the isometries are, from now, worth taking into consideration