Image compression using DCT and compressive sensing (CS) theory

Abstract

Data compression is a method of storing the same information with less data or space. There are many techniques available for compressing the image data resulting in reduced storage space. Minimizing storage space minimizes the bandwidth required for transmission. This research work presents an image compression technique that uses the discrete cosine transform (DCT) and compressive sensing (CS) theory. The original image is first down-sampled. DCT is applied to this reduced size image and only significant coefficients are selected to represent the original image. In order to decompress the data, first the inverse DCT is taken on the transformed coefficients and the resultant image is divided into blocks. Then a database of original and down-sampled images is used to learn the best match. These blocks for which we do not find the match are estimated using CS theory. The results are compared with the JPEG and state of the art method.