The growth of digital image and video archives is increasing the need for tools that effectively filter and efficiently search through large amounts of visual data. Towards this goal we propose a technique by which the color content of images and videos is automatically extracted to form a class of meta-data that is easily indexed. The color indexing algorithm uses the back-projection of binary color sets to extract color regions from images. This technique provides for both the automated extraction of regions and representation of their color content. It overcomes some of the problems with color histogram techniques such as high-dimensional feature vectors, spatial localization, indexing and distance computation. We present the binary color set back-projection technique and discuss its implementation in the VisualSEEk content-based image/video retrieval system for the World Wide Web. We also evaluate the retrieval effectiveness of the color set back-projection method and compare its performance to other color retrieveal methods.

We investigate the consequences of maximizing information transfer in a simple neural network (one input layer, one output layer), focussing on the case of non linear transfer functions. We assume that both receptive fields (synaptic efficacies) and transfer functions can be adapted to the environment. The main result is that, for bounded and invertible transfer functions, in the case of a vanishing additive output noise, and no input noise, maximization of information (Linsker'sinfomax principle) leads to a factorial code - hence to the same solution as required by the redundancy reduction principle of Barlow. We show also that this result is valid for linear, more generally unbounded, transfer functions, provided optimization is performed under an additive constraint, that is which can be written as a sum of terms, each one being specific to one output neuron. Finally we study the effect of a non zero input noise. We find that, at first order in the input noise, assumed to be small ...

Construction toys are a superb medium for creating geometric models. We argue that such toys, suitably instrumented or sensed, could be the inspiration for a new generation of easy-to-use, tangible modeling systems---especially if the tangible modeling is combined with graphical-interpretation techniques for enhancing nascent models automatically. The three key technologies needed to realize this idea are embedded computation, vision-based acquisition, and graphical interpretation. We sample these technologies in the context of two novel modeling systems: physical building blocks that self-describe, interpret, and decorate the structures into which they are assembled; and a system for scanning, interpreting, and animating clay figures. In Proceedings of SIGGRAPH 2000, July 23-28, 2000. New Orleans, Louisiana, USA. This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted ...

Figure 1: Shaded, volume rendered spheres stored with two values per voxel: a value indicating the distance to the closest surface point; and a binary intensity value. The sphere in a) has radius 30 voxels and is stored in an array of size. The spheres in b), c), and d) have radii 3 voxels, 2 voxels and 1.5 voxels respectively and are stored in arrays of size. The surface normal used in surface shading was calculated using a 6-point central difference operator on the distance values. Remarkably smooth shading can be achieved for these low resolution data volumes because the function of the distance-to-closest surface varies smoothly across surfaces. (See color plate.) High quality rendering and physics-based modeling in volume graphics have been limited because intensity-based volumetric data do not represent surfaces well. High spatial frequencies due to abrupt intensity changes at object surfaces result in jagged or terraced surfaces in rendered images. The use of a distance-to-closestsurface function to encode object surfaces is proposed. This function varies smoothly across surfaces and hence can be accurately reconstructed from sampled data. The zero-value iso-surface of the distance map yields the object surface and the derivative of the distance map yields the surface normal. Examples of rendered images are presented along with a new method for calculating distance maps from sampled binary data.

We present a computational model for periodic pattern perception based on the mathematical theory of crystallographic groups. In each N-dimensional Euclidean space, a finite number of symmetry groups can characterize the structures of an infinite variety of periodic patterns. In 2D space, there are seven frieze groups describing monochrome patterns that repeat along one direction and 17 wallpaper groups for patterns that repeat along two linearly independent directions to tile the plane. We develop a set of computer algorithms that "understand" a given periodic pattern by automatically finding its underlying lattice, identifying its symmetry group, and extracting its representative motifs. We also extend this computational model for near-periodic patterns using geometric AIC. Applications of such a computational model include pattern indexing, texture synthesis, image compression, and gait analysis.

In this paper we propose a method for automatic color extraction and indexing to support color queries of image and video databases. This approach identifies the regions within images that contain colors from predetermined color sets. By searching over a large number of color sets, a color index for the database is created in a fashion similar to that for file inversion. This allows very fast indexing of the image collection by color contents of the images. Furthermore, information about the identified regions, such as the color set, size, and location, enables a rich variety of queries that specify both color content and spatial relationships of regions. We present the single color extraction and indexing method and contrast it to other color approaches. We examine single and multiple color extraction and image query on a database of 3000 color images. 1

Abstract – A new stereo vision tracker setup for virtual and augmented reality applications is presented in this paper. Performance, robustness and accuracy of the system are achieved under real-time constraints. The method is based on blobs extraction, two-dimensional prediction, the epipolar constraint and three-dimensional reconstruction. Experimental results using a stereo rig setup (equipped with IR capabilities) and retroreflective targets are presented to demonstrate the capabilities of our optical tracking system. The system tracks up to 25 independent targets at 30 Hz.

Automatic program specialization can derive e#cient implementations from generic components, thus reconciling the often opposing goals of genericity and e#ciency. This technique has proved useful within the domains of imperative, functional, and logical languages, but so far has not been explored within the domain of object-oriented languages.

We present a volumetric method that can efficiently create triangular meshes from 3-D geometric data. This data can be presented in the form of images, profiles or unordered points. The mesh model can be created at different resolutions and can also be closed to make a true volumetric model.

Abstract not found