ICA-Based Algorithms Applied to Image Coding

9 years 7 months ago
ICA-Based Algorithms Applied to Image Coding
Recently, Narozny et al [1] proposed a new viewpoint in variable high-rate transform coding. They showed that the problem of finding the optimal 1-D linear block transform for a coding system employing entropy-constrained uniform quantization may be viewed as a modified independent component analysis (ICA) problem. By adopting this new viewpoint, two new ICA-based algorithms, called GCGsup and ICAorth, were then derived for computing respectively the optimal linear transform and the optimal orthogonal transform. In this paper, we show that the transforms returned by GCGsup and ICAorth can achieve better visual image quality (better preservation of lines and contours) than the KLT and 2-D Discrete Cosine Transform (DCT) when applied to the compression of well-known grayscale images.
Michel Narozny, Michel Barret
Added 02 Jun 2010
Updated 02 Jun 2010
Type Conference
Year 2007
Authors Michel Narozny, Michel Barret
Comments (0)