Lossy compression through segmentation on low depth-of-field images

The popularity of multimedia applications has resulted in development of lossless and lossy compression techniques. This paper presents a novel lossy compression scheme for the low depth-of-field (DOF) images where the quality factor is altered based on whether we are compressing object-of-interest (OOI) or the background. The proposed method involves segmentation of OOI and then the application of lossy scheme. The experimental results shows that the proposed method performs well in compressing the given image (higher compression ratio), at the same time maintaining the acceptable quality (high PSNR).