New approach for retrieve images by using DCT blocks

Information extraction of the images and videos has been done in pixel domain by the traditional methods. But nowadays, great majority of pictures and video are available in compressed form with compression based on block DCT transform. In this paper, we proposed a method based on the DCT blocks for retrieve compressed images. By working on wei-feb and faces94 databases, we show that using the DCT normal blocks, their average and variance instead of using the main pixel of blocks can improve the results.