Prediction of Parameters in Optimal Operation Point for BPG-based Lossy Compression of Noisy Images

Abstract

Lossy compression of images corrupted by noise has several peculiarities. First, a specific noise filtering effect is observed. Second, optimal operation point (OOP) can be observed, i.e. such coder parameter (e.g., quantization step) value can exist that quality of compressed image calculated with respect to noise-free image can be better compared to quality of uncompressed (original noisy) image. If OOP exists, it is worth compressing a given image in OOP, if no, other recommendations on coder parameter setting are reasonable. Since noise-free image is not available in practice, it is not possible to determine does OOP exist and what is image quality in it. In this paper, we show that OOP existence for several quality metrics can be predicted quite easily and quickly for grayscale images corrupted by additive white Gaussian noise and compressed by better portable graphics (BPG) encoder. Such a prediction is based on analysis of statistics of discrete cosine transform (DCT) coefficients calculated for a limited number of 8x8 pixel blocks. A scatter-plot of metric improvement (reduction) depending upon these statistics is obtained in advance and prediction curve fitting is performed. Recommendations on encoder parameter setting for cases of OOP absence are given.