An Efficient Block-based Image Compression And Quality-Wise Decompression Algorithm

In this paper, we propose a block-based lossy image compression algorithm that makes use of spatial redundancies of neighboring pixels in image data. Compression is achieved by replacing a block of pixels with their statistical mean. The algorithm helps in decompressing the image at different quality levels. Quality matrices constructed from the quantization table of the JPEG baseline algorithm are used to achieve different qualities of the reconstructed data. Experimental results show that the proposed method outperforms existing polynomial-based algorithms both in computation time and complexity.