Low PSNR High Fidelity Image Compression Using Surrounding Pixels
Tanuja R. Patil, Vishwanath P. Baligar, Roopa P. Huilgol · 2018
Data compression is important to reduce the transmission delays and to ensure efficient utilization of bandwidth and storage space. As images constitute a major part of the data being stored and communicated, image compression is of great importance. However, compression should not degrade the quality of the image to an unacceptable level. This paper presents a high fidelity image compression algorithm which scans the image in the form of 3*3 overlapping blocks, and compresses the image by extracting the information about the centre pixel and the pixels surrounding the centre pixel within the blocks. Decompression uses an iterative approach to reconstruct the image from the centre pixels and their neighbors. The proposed algorithm offers high quality at lower Peak Signal to Noise Ratio (PSNR) values. Also, a new quality metric is proposed and is used to compare the results with JPEG lossy approach. Results reveal that the quality of the decompressed image obtained by the proposed algorithm is better than that of JPEG lossy algorithm at same PSNR values.