JPEG-based Variable Block-Size Image Compression using CIE Lab Color Space

In this work we propose a compression technique that makes use of linear and perceptually uniform CIE La*b* color space in the JPEG image compression framework to improve its performance at lower bitrates. To generate quantization matrices suitable for the linear and perceptually uniform CIE La*b* color space, a novel linear Contrast Sensitivity Function (CSF) is used. The compression performance in terms of Compression Ratio (CR) and Peak Signal to Noise Ratio (PSNR), is further improved by utilizing image dependent, variable and non-uniform image sub-blocks generated using a proposed histogram-based merging technique. Experimental results indicate that the proposed linear CSF based quantization technique yields, on an average, 8% increase in CR for the same reconstructed image quality in terms of PSNR as compared to the conventional YCbCr color space. The proposed scheme also outperforms JPEG in terms of CR by an average of 45.01% for the same reconstructed image quality.