Pixelization Paradigm: Visual Information Expert Workshop, VIEW 2006, Paris, France, April 24-25, 2006, Revised Selected Papers(Image Processing, Computer Vision, Pattern Recognition, and Graphics)

The pixelization paradigm states as a postulate that pixelization methods are rich and are worth exploring as far as possible. In fact, we think that the strength of these methods lies in their simplicity, in their high-density way of information representation property and in their compatibility with neurocognitive processes. • Simplicity, because pixelization belongs to two-dimensional information visualization methods and its main idea is identifying a “pixel” with an informational entity in order to translate a set of informational entities into an image. • High-density way of information representation property, firstly because pixelization representation contains a third dimension—each pixel’s color—and secondly because pixelization is a “compact” (two-dimensional) way of representing information compared with linear one-dimensional representations (Ganascia, p.255) . • Compatibility with neurocognitive processes, firstly because we are thr- dimensional beings and thus we are intrinsically better at grasping one- or two-dimensional data, and secondly because the cerebral cortex is typically a bi-dimensional structure where metaphorically the neurons can be assimilated to “pixels,” whose activity plays the role of color (Lévy, p.3). The pixelization paradigm may be studied along two related directions: pixelization and its implementation and pixelization and cognition. The first direction—pixelization and its implementation—may be divided into two parts: pixelization theory and pixelization application.

Table of Contents:
Pixelization Theory.- Pixelization Paradigm: Outline of a Formal Approach.- Scalable Pixel Based Visual Data Exploration.- High Dimensional Visual Data Classification.- Using Biclustering for Automatic Attribute Selection to Enhance Global Visualization.- Pixelisation-Based Statistical Visualisation for Categorical Datasets with Spreadsheet Software.- Dynamic Display of Turnaround Time Via Interactive 2D Images.- Pixelizing Data Cubes: A Block-Based Approach.- Leveraging Layout with Dimensional Stacking and Pixelization to Facilitate Feature Discovery and Directed Queries.- Online Data Visualization of Multidimensional Databases Using the Hilbert Space–Filling Curve.- Pixel-Based Visualization and Density-Based Tabular Model.- Pixelization Applications.- A Geometrical Approach to Multiresolution Management in the Fusion of Digital Images.- Analysis and Visualization of Images Overlapping: Automated Versus Expert Anatomical Mapping in Deep Brain Stimulation Targeting.- A Computational Method for Viewing Molecular Interactions in Docking.- A Graphical Tool for Monitoring the Usage of Modules in Course Management Systems.- Visu and Xtms: Point Process Visualisation and Analysis Tools.- Visualizing Time-Course and Efficacy of In-Vivo Measurements of Uterine EMG Signals in Sheep.- From Endoscopic Imaging and Knowledge to Semantic Formal Images.- Multiscale Scatterplot Matrix for Visual and Interactive Exploration of Metabonomic Data.- ICD-View: A Technique and Tool to Make the Morbidity Transparent.- Pixelization and Cognition.- Time Frequency Representation for Complex Analysis of the Multidimensionality Problem of Cognitive Task.- Instant Pattern Filtering and Discrimination in a Multilayer Network with Gaussian Distribution of the Connections.- AC3 – AutomaticCartography of Cultural Contents.- Evaluation of the Mavigator.