Self-organizing map-based color palette for high-dynamic range texture compression

Abstract

High-dynamic range (HDR) images are commonly used in computer graphics for accurate rendering. However, it is inefficient to store these images because of their large data size. Although vector quantization approach can be used to compress them, a large number of representative colors are still needed to preserve acceptable image quality. This paper presents an efficient color quantization approach to compress HDR images. In the proposed approach, a 1D/2D neighborhood structure is defined for the self-organizing map (SOM) approach and the SOM approach is then used to train a color palette. Afterward, a virtual color palette that has more codevectors is simulated by interpolating the trained color palette. The interpolation process is hardware supported in the current graphics hardware. Hence, there is no need to store the virtual color palette as the representative colors are constructed on the fly. Experimental results show that our approach can obtain good image quality with a moderate color palette.Keywords Self-organizing map (SOM) Á Color quantization Á High-dynamic range (HDR) Á Large color palette virtualization (LCPV)

NP-SOM: Network Programmable Self-Organizing Maps

“…We consider a well-known application of vector quantization: lossy image compression [12]. A picture or series of pictures to be compressed is split into smaller kˆk pixels wide thumbnails.…”

Novelty Detection with Self-Organizing Maps for Autonomous Extraction of Salient Tracking Features

“…Novelty detection relies on these properties by detecting elements that are too far from the neural clusters and that do not fit the topology learned. These properties can be interestingly applied to the image processing field, as in [2] or [16]. Our aim is to use these models to perform novelty detection within images without any prior knowledge, so as to be able to extract unexpected targets from image sequences and track them.…”

Smart motion detection sensor based on video processing using self-organizing maps

“…Hence this artificial neural network has had a wide range of application fields over the decades (Samuel Kaski and Kohonen, 1998;Oja et al, 2003). In particular, it has been applied to several areas of computer vision, such as color quantization (Dekker, 1994;Papamarkos, 1999;Xiao et al, 2012;Palomo and Domínguez, 2014), and image segmentation (Bhandarkar et al, 1997;Dong and Xie, 2005;Maddalena and Petrosino, 2008a;Lacerda and Mello, 2013). The SOM is based on an incremental (online) learning process, which has better ability to escape from local minima than batch learning (Bermejo and Cabestany, 2002) and consumes less computational time in color quantization problems (Chang et al, 2005).…”