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-organizi… Show more
“…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.…”
Self-organizing maps (SOM) are a wellknown and biologically plausible model of input-driven selforganization that has shown to be effective in a wide range of applications. We want to use SOMs to control the processing cores of a massively parallel digital reconfigurable hardware, taking into account the communication constraints of its underlying network-on-chip (NoC) thanks to bio-inspired principles of structural plasticity. Although the SOM accounts for synaptic plasticity, it doesn't address structural plasticity. Therefore we have developed a model, namely the NP-SOM (network programmable self-organizing map), able to define SOMs with different underlying topologies as the result of a specific configuration of the associated NoC. To gain insights on a future introduction of advanced structural plasticity rules that will induce dynamic topological modifications, we investigate and quantify the effects of different hardwarecompatible topologies on the SOM performance. To perform our tests we consider a lossy image compression as an illustrative application.
“…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.…”
Self-organizing maps (SOM) are a wellknown and biologically plausible model of input-driven selforganization that has shown to be effective in a wide range of applications. We want to use SOMs to control the processing cores of a massively parallel digital reconfigurable hardware, taking into account the communication constraints of its underlying network-on-chip (NoC) thanks to bio-inspired principles of structural plasticity. Although the SOM accounts for synaptic plasticity, it doesn't address structural plasticity. Therefore we have developed a model, namely the NP-SOM (network programmable self-organizing map), able to define SOMs with different underlying topologies as the result of a specific configuration of the associated NoC. To gain insights on a future introduction of advanced structural plasticity rules that will induce dynamic topological modifications, we investigate and quantify the effects of different hardwarecompatible topologies on the SOM performance. To perform our tests we consider a lossy image compression as an illustrative application.
“…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.…”
In the image processing field, many tracking algorithms rely on prior knowledge like color, shape or even need a database of the objects to be tracked. This may be a problem for some real world applications that cannot fill those prerequisite. Based on image compression techniques, we propose to use Self-Organizing Maps to robustly detect novelty in the input video stream and to produce a saliency map which will outline unusual objects in the visual environment. This saliency map is then processed by a Dynamic Neural Field to extract a robust and continuous tracking of the position of the object. Our approach is solely based on unsupervised neural networks and does not need any prior knowledge, therefore it has a high adaptability to different inputs and a strong robustness to noisy environments.
“…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).…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.