Information Theory, 2004. ISIT 2004. Proceedings. International Symposium on

13-15 Oct. 2004

Filter Results

Displaying Results 1 - 25 of 49
  • Proceedings. 33rd Applied Imagery Pattern Recognition Workshop

    Publication Year: 2004
    Request permission for commercial reuse | PDF file iconPDF (66 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2004, Page(s):v - viii
    Request permission for commercial reuse | PDF file iconPDF (42 KB)
    Freely Available from IEEE
  • Preface

    Publication Year: 2004, Page(s): ix
    Request permission for commercial reuse | PDF file iconPDF (24 KB) | HTML iconHTML
    Freely Available from IEEE
  • AIPR Executive Committee

    Publication Year: 2004, Page(s): x
    Request permission for commercial reuse | PDF file iconPDF (22 KB)
    Freely Available from IEEE
  • Erratum [for paper published in the 2003 Proceedings]

    Publication Year: 2004, Page(s): xi
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (23 KB)

    Erratum for paper published in the 2003 Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop. Paper number AIPR0336 printed on pages 221 to 225 of the proceedings: the title and authors as printed in the proceedings are listed below: Quick Response Airborne Deployment of Viper Muzzle Flash Detection and Location System During DC Sniper Attacks M. Pauli**, M.C. Ertem*, E. Heidhausen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple-aperture imaging spectrometer: computer simulation and experimental validation

    Publication Year: 2004, Page(s):3 - 9
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB) | HTML iconHTML

    The Lockheed Martin Advanced Technology Center (LMVATC) is actively investigating alternate applications of coherently phased sparse-aperture optical imaging arrays. Controlling the relative phasing of the apertures enables these arrays to function as imaging interferometers, providing high spectral resolution as well as high spatial resolution imagery. In this paper we: a) summarize the basic the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusion of intensity, texture, and color in video tracking based on mutual information

    Publication Year: 2004, Page(s):10 - 15
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (888 KB) | HTML iconHTML

    Next-generation reconnaissance systems (NGRS) offer dynamic tasking of a menu of sensor modalities such as video, multi/hyper-spectral and polarization data. A key issue is how best to exploit these modes in time critical scenarios such as target tracking and event detection. It is essential to be able to represent diverse sensor content in a unified measurement space so that the contribution of e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive road detection through continuous environment learning

    Publication Year: 2004, Page(s):16 - 21
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB) | HTML iconHTML

    The Intelligent Systems Division of the National Institute of Standards and Technology has been engaged for several years in developing real-time systems for autonomous driving. A road detection program is an essential part of the project. Previously we developed an adaptive road detection system based on color histograms using a neural network. This, however, still required human involvement duri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimizing uncertainty in determinants and ratios of determinants for invariant relationships employed in SAR imagery pattern recognition

    Publication Year: 2004, Page(s):22 - 27
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB) | HTML iconHTML

    Invariant relationships involving ratios of determinants have been proposed for the classification of an object in SAR imagery. The target detection decision-making process depends on the uncertainty involved in the measurements. At fixed experimental resolution, some determinants are simply better than others because they are much less sensitive to uncertainty. A geometrical interpretation of det... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual adaptation of scale and imprecision in a noisy world

    Publication Year: 2004, Page(s):28 - 32
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (120 KB) | HTML iconHTML

    Pointlike quantum noise in an image can be defeated either by representing the image at a low gray-scale resolution or at a low spatial resolution. The first solution locates an image at an inherent imprecision, and the second locates the image at an inherent spatial scale. Two vision-based models combat noise by automatic and local spatial-scale adjustment. Making contrast steps proportional to t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced algorithms for autonomous hyperspectral change detection

    Publication Year: 2004, Page(s):33 - 38
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1080 KB) | HTML iconHTML

    Persistent ISR (intelligence surveillance and reconnaissance) has proven its value as a tactic for national defense. This activity can collect, in particular, information necessary for executing an important concept of operations: wide-area autonomous change detection over long time intervals. Here we describe the remarkable potential of hyperspectral remote sensing systems for enabling such missi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust detection and recognition of buildings in urban environments from LADAR data

    Publication Year: 2004, Page(s):39 - 44
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1064 KB) | HTML iconHTML

    Successful unmanned ground vehicle (UGV) navigation in urban areas requires the competence of the vehicle to cope with Global Positioning System (GPS) outages and/or unreliable position estimates due to multipathing. At the National Institute of Standards and Technology (NIST) we are developing registration algorithms using LADAR (LAser Detection And Ranging) data to cope with such scenarios. In t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multiresolution time domain approach to RF image formation

    Publication Year: 2004, Page(s):45 - 47
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (80 KB) | HTML iconHTML

    Conventional image formation approaches rely on frequency domain Fourier methods to create images of objects. Most rely on integrating spatial resolution in the Fourier domain and do not accurately factor in the spatial aperture function to create an image because of the uniform spatial sampling necessary for the Fourier transform. We propose a multiresolution approach based on a Greens function i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image primitive signatures

    Publication Year: 2004, Page(s):51 - 54
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1400 KB) | HTML iconHTML

    Image signatures are generated from the comparison of segments contained within an image to a database of segments collected over a large variety of images. It is impossible to retain all of the segments from all of the images so the segments are clustered becomes an image primitive as each cluster contains a unique set of similar segments. The size of the image signature is NK where N is the numb... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture discrimination and classification using pulse images

    Publication Year: 2004, Page(s):55 - 60
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4336 KB) | HTML iconHTML

    Neural models of the mammalian visual cortex have been used in digital image processing for many years. The neural models have demonstrated a robust talent for extracting image segments that are inherent in the image. This paper explores the use of a simple neural model for the extraction of texture information. The neural firing patterns in the model are dependent upon the input texture and by ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Biologically inspired approaches to automated feature extraction and target recognition

    Publication Year: 2004, Page(s):61 - 66
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB) | HTML iconHTML

    Ongoing research at Boston University has produced computational models of biological vision and learning that embody a growing corpus of scientific data and predictions. Vision models perform long-range grouping and figure/ground segmentation, and memory models create attentionally controlled recognition codes that intrinsically combine bottom-up activation and top-down learned expectations. Thes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complex neural networks as future tools in imagery analysis

    Publication Year: 2004, Page(s):67 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB) | HTML iconHTML

    Brain networks are uniquely capable of generating and integrating information collected from multiple sources in real time. The application of structural and information theoretical measures to such networks has begun to unravel the crucial ingredients that ensure their rapid and robust performance. We suggest the use of information theoretical measures in applications that mimic some of these bio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computation in the higher visual cortices: map-seeking circuit theory and application to machine vision

    Publication Year: 2004, Page(s):73 - 78
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB) | HTML iconHTML

    Map-seeking circuit theory is a biologically based computational theory of vision applicable to difficult machine vision problems such as recognition of 3D objects in arbitrary poses amid distractors and clutter, as well as to non-recognition problems such as terrain interpretation. It provides a general computational mechanism for tractable discovery of correspondences in massive transformation s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neurally-based algorithms for image processing

    Publication Year: 2004, Page(s):79 - 85
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB) | HTML iconHTML

    One of the more difficult problems in image processing is segmentation. The human brain has an ability that is unmatched by any current technology for breaking down the world into distributed features and reconstructing them into distinct objects. Neurons encode information both in the number of spikes fired in a given time period, which indicates the strength with which a given local feature is p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward view-invariant representations of object structure learned using object constancy cues in natural movies

    Publication Year: 2004, Page(s):86 - 91
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB) | HTML iconHTML

    An approach to learning view-invariant object representations was explored based on the learning of legal or naturalistic view transformations in time, learned from the statistical properties of natural movies. A simple cell layer responded to localized oriented image structure, and a complex cell layer learned to respond to those subsets of simple cells with the strongest tendencies to trade off ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised fuzzy-membership estimation of terms in semantic and syntactic lexical classes

    Publication Year: 2004, Page(s):95 - 100
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB) | HTML iconHTML

    The objective of this research is to discover fuzzy semantic and syntactic relationships among English words at various levels of abstraction without using any other sources of semantic or syntactical reference information (e.g. dictionaries, lexicons, grammar rules, etc...) An agglomerative clustering algorithm is applied to the co-occurrence space formed by subsets of target words and training w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy find matching tool for image text analysis

    Publication Year: 2004, Page(s):101 - 105
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (91 KB) | HTML iconHTML

    In this paper, we present a study based on the effect of using a fuzzy find matching technique with the objective of increasing the precision of textual information retrieval for image analysis while allowing for mismatches. This technique is very helpful for searching those areas of interest where chances of misspelling are more likely, for example retrieving text information from an image. The t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mountain clustering on nonuniform grids

    Publication Year: 2004, Page(s):106 - 111
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB) | HTML iconHTML

    We describe an improvement on the mountain method (MM) of clustering originally proposed by Yager and Filev. The new technique employs a data-driven, hierarchical partitioning of the data set to be clustered, using a "p-tree" algorithm. The centroids of data subsets in the terminal nodes of the p-tree are the set of candidate cluster centers to which the iterative candidate cluster center selectio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Swarmed feature selection

    Publication Year: 2004, Page(s):112 - 118
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (152 KB) | HTML iconHTML

    Feature selection is an important part of pattern recognition, helping to overcome the curse of dimensionality problem with classifiers, among other systems. In this work, we introduce a feature selection method using particle swarm optimization. Experiments using data of others and hyperspectral remote sensed data are used to measure the performance of the algorithm. Its comparison with a genetic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Designing templates for cellular neural networks using particle swarm optimization

    Publication Year: 2004, Page(s):119 - 123
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (160 KB) | HTML iconHTML

    Designing or learning of templates for cellular neural networks constitutes one of the crucial research problems of this paradigm. In this work, we present the use of a particle swarm optimizer, a global search algorithm, to design a template set for a CNN. A brief overview of the algorithms and methods is given. Design of popular templates is performed using the search algorithm described. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.