Image Compression with SVD : A New Quality Metric Based On Energy Ratio
This addresses a specific issue for image compression researchers by providing a more accurate metric for SVD-based methods, though it is incremental as it builds on existing quality assessment techniques.
The paper tackles the problem of measuring quality for images compressed with singular value decomposition (SVD), proposing a new metric based on energy ratio, which shows that for a rank k=40, 99.9% of energy is restored with SSIM=0.94 or PSNR=35 dB.
Digital image compression is a technique that allows to reduce the size of an image in order to increase the capacity storage devices and to optimize the use of network bandwidth. The quality of compressed images with the techniques based on the discrete cosine transform or the wavelet transform is generally measured with PSNR or SSIM. Theses metrics are not suitable to images compressed with the singular values decomposition. This paper presents a new metric based on the energy ratio to measure the quality of the images coded with the SVD. A series of tests on 512 * 512 pixels images show that, for a rank k = 40 corresponding to a SSIM = 0,94 or PSNR = 35 dB, 99,9% of the energy are restored. Three areas of image quality assessments were identified. This new metric is also very accurate and could overcome the weaknesses of PSNR and SSIM.