IMAGE COMPRESSION WITHOUT VISUALLY VISIBLE DISTORTIONS

A.N. Zemlyachenko, V.V. Lukin

Methods for lossy compression of images without visual visible distortions are considered. Metrics PSNR-HVS-M and MSSIM are used for controlling visual quality of compressed images. The dependency of the compression ratio on the values of the metrics PSNR-HVS-M and MSSIM preset by the user is considered. The results of compression for different test images and coders are presented. The comparative analysis is carried out, the recommendations on the coder use are given. It is shown that the compression ratio greatly depends on such features of the compressed images as complexity of information content and level of the noise.

Keywords: compression ratio, lossy compression, image visual quality metrics.