Results 1  10
of
310
Tools and Techniques for Color Image Retrieval
, 1996
"... 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 ..."
Abstract

Cited by 171 (12 self)
 Add to MetaCart
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 metadata that is easily indexed. The color indexing algorithm uses the backprojection 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 highdimensional feature vectors, spatial localization, indexing and distance computation. We present the binary color set backprojection technique and discuss its implementation in the VisualSEEk contentbased image/video retrieval system for the World Wide Web. We also evaluate the retrieval effectiveness of the color set backprojection method and compare its performance to other color retrieveal methods.
Non Linear Neurons in the Low Noise Limit: A Factorial Code Maximizes Information Transfer
, 1994
"... 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 environm ..."
Abstract

Cited by 143 (18 self)
 Add to MetaCart
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 ...
A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2004
"... We present a computational model for periodic pattern perception based on the mathematical theory of crystallographic groups. In each Ndimensional Euclidean space, a finite number of symmetry groups can characterize the structures of an infinite variety of periodic patterns. In 2D space, there ar ..."
Abstract

Cited by 69 (17 self)
 Add to MetaCart
We present a computational model for periodic pattern perception based on the mathematical theory of crystallographic groups. In each Ndimensional 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 nearperiodic patterns using geometric AIC. Applications of such a computational model include pattern indexing, texture synthesis, image compression, and gait analysis.
Using distance maps for accurate surface representation in sampled volumes
 In IEEE Vol. Vis
, 1998
"... 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 ..."
Abstract

Cited by 63 (4 self)
 Add to MetaCart
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 6point central difference operator on the distance values. Remarkably smooth shading can be achieved for these low resolution data volumes because the function of the distancetoclosest surface varies smoothly across surfaces. (See color plate.) High quality rendering and physicsbased modeling in volume graphics have been limited because intensitybased 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 distancetoclosestsurface function to encode object surfaces is proposed. This function varies smoothly across surfaces and hence can be accurately reconstructed from sampled data. The zerovalue isosurface 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.
Tangible interaction + graphical interpretation: a new approach to 3d modeling
 In Proc. SIGGRAPH ’00, ACM Press/AddisonWesley Publishing Co
"... 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 easytouse, tangible modeling systems—especially if the tangible modeling is combined with graphicalinterpretation techniqu ..."
Abstract

Cited by 58 (2 self)
 Add to MetaCart
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 easytouse, tangible modeling systems—especially if the tangible modeling is combined with graphicalinterpretation techniques for enhancing nascent models automatically. The three key technologies needed to realize this idea are embedded computation, visionbased acquisition, and graphical interpretation. We sample these technologies in the context of two novel modeling systems: physical building blocks that selfdescribe, interpret, and decorate the structures into which they are assembled; and a system for scanning, interpreting, and animating clay figures.
Single color extraction and image query
 in Proceedings of the 2nd IEEE International Conference on Image Processing
, 1995
"... ..."
A new optical tracking system for virtual and augmented reality applications
 In Proceedings of the IEEE Instrumentation and Measurement Technical Conference
, 2001
"... 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 realtime constraints. The method is based on blobs extraction, twodimensional prediction, the epipolar const ..."
Abstract

Cited by 50 (6 self)
 Add to MetaCart
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 realtime constraints. The method is based on blobs extraction, twodimensional prediction, the epipolar constraint and threedimensional 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.
Towards Automatic Specialization of Java Programs
 In Proceedings of the European Conference on Objectoriented Programming (ECOOP'99
, 1999
"... 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 explore ..."
Abstract

Cited by 41 (12 self)
 Add to MetaCart
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 objectoriented languages.
Histogram Equalization of the Speech Representation for Robust Speech Recognition
, 2001
"... The noise degrades the performance of Automatic Speech Recognition systems mainly due to the mismatch between the training and recognition conditions it introduces. The noise causes a distortion of the feature space which usually presents a nonlinear behavior. In order to reduce this mismatch, the ..."
Abstract

Cited by 37 (3 self)
 Add to MetaCart
The noise degrades the performance of Automatic Speech Recognition systems mainly due to the mismatch between the training and recognition conditions it introduces. The noise causes a distortion of the feature space which usually presents a nonlinear behavior. In order to reduce this mismatch, the methods proposed for robust speech recognition try to compensate the noise effect either by obtaining an estimation of the clean speech or by adapting the recognizer acoustic models for a proper modeling of the noisy speech. In this paper we propose a method to compensate the noise effect over the speech representation. This method is based on the histogram equalization technique frequently applied for Digital Image Processing, which has been adapted to the speech representation. For each component of the feature vectors representing the speech signal, the histogram is estimated and the transformation which converts it into a reference histogram is calculated. Such transformations tend to compensate the distortion the noise produces over the different components of the feature vector and improve the performance of the recognition systems under noise conditions. We describe how the histogram equalization method can be adapted to robust speech recognition and present some recognition experiments to evaluate the proposed method.