4th IEEE Southwest Symposium on Image Analysis and Interpretation

2-4 April 2000

Filter Results

Displaying Results 1 - 25 of 61
  • 4th IEEE Southwest Symposium on Image Analysis and Interpretation

    Publication Year: 2000
    Request permission for commercial reuse | PDF file iconPDF (323 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2000, Page(s):310 - 311
    Request permission for commercial reuse | PDF file iconPDF (9 KB)
    Freely Available from IEEE
  • Overcomplete image representations and locally best model selection

    Publication Year: 2000, Page(s):68 - 72
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (112 KB)

    In this paper we formulate a general modeling framework that unifies and extends several state-of-the-art statistical image processing methodologies, including translation-invariant wavelet methods, overcomplete image representations, and best basis selection. At the heart of this framework is a novel hierarchical image model that combines/fuses several basis systems into a single observed image r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Foveated video image analysis and compression gain measurements

    Publication Year: 2000, Page(s):63 - 67
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (300 KB)

    We present a framework for assessing the quality of, and determining the efficiency of foveated and compressed images and video streams. We develop unique algorithms for assessing the quality of foveated image/video data. By interpreting foveation as a coordinate transformation, we analyze the increase in compression efficiency that is afforded by our foveation approach. We demonstrate these conce... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using moment invariants and HMM in facial expression recognition

    Publication Year: 2000, Page(s):305 - 309
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1648 KB)

    Moment invariants are invariant under shifting, scaling and rotation. They are widely used in pattern recognition because of their discrimination power and robustness. The HMM method is natural and highly reliable way of recognition. In this paper we propose a method for using moment invariants as features and HMM as the recognition method in facial expression recognition. Sequences of four univer... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network approach to geographic image analysis

    Publication Year: 2000, Page(s):58 - 62
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    We have developed a method based on the precise pixel-to-pixel matching between two images. This is done by automatic generation of displacement vectors, carrying the information of differences between the two images. For generating a layer of vectors defining the information of displacement we use a neural network with self-learning architecture. The proposed algorithm perform successful mapping,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture classification using dominant wavelet packet energy features

    Publication Year: 2000, Page(s):301 - 304
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (84 KB)

    This paper proposes a high performance texture classification method using dominant energy features from wavelet packet decomposition. We decompose the texture images with a family of real orthonormal wavelet bases and compute the energy signatures using the wavelet packet coefficients. Then we select a few of the most dominant energy values as features and employ a Mahalanobis distance classifier... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gradual shot transition detection based on multidimensional clustering

    Publication Year: 2000, Page(s):53 - 57
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB)

    Detection of shot transitions in video material is a process intended to ease the automatic extraction of video features for later use in indexing and retrieval purposes. While abrupt shot transitions are discontinuities quite easy to detect, the gradual ones are highly masked by and confused with object motion, camera operation, and other disturbing effects. Current approaches to detecting gradua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer assisted landmarking of cephalometric radiographs

    Publication Year: 2000, Page(s):296 - 300
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    We address the problem of finding an initial estimation of the location of landmarks on an image, when the landmarks are difficult to distinguish on the image and when the locations are dependent together from external forces such as growth. Our method solves the problem using an adaptive coordinate space where locations are registered. In this space, variability is greatly reduced. A training set... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modulation domain image segmentation

    Publication Year: 2000, Page(s):46 - 50
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (148 KB)

    We present a modulation domain technique for segmenting textured images modeled as 2D multicomponent AM-FM functions. A Gabor filter bank is used to derive estimates of the dominant modulations at each image point and statistical clustering is then performed with respect to a similarity measure-based modulation domain entropy. Post processing is applied in the image domain to regularize the soluti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Statistical gait description via temporal moments

    Publication Year: 2000, Page(s):291 - 295
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (84 KB)

    Statistical recognition techniques have already been shown to achieve good performance in automatic gait recognition. However, the metrics were only statistical in nature and did not describe the intimate nature of gait. Accordingly, new velocity moments have been developed to describe an object and its motion throughout an image sequence. These moments are an extended form of centralised moments ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation techniques for object-based coding

    Publication Year: 2000, Page(s):41 - 45
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (100 KB)

    Two image segmentation methods are presented and compared terms of rate-distortion within an object-based coding scheme. The LOMO segmentation exploits the relationship between mathematical morphology and local monotonicity in producing a multiscale segmentation. The process is a morphological analogy to the Laplacian of Gaussian. The level set approach used area morphology to generate segmented r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lower-level and higher-level approaches to content-based image retrieval

    Publication Year: 2000, Page(s):197 - 201
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    This paper describes a content-based image retrieval system that employs both higher-level and lower-level vision methodologies separately and in conjunction the retrieval of images containing large man-made objects. The goal is to use the lower-level analysis module to increase the capability of the higher-level analysis module, for queries where the structure exhibited by the manmade objects is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A integrated color-spatial image representation and the similar image retrieval

    Publication Year: 2000, Page(s):283 - 287
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (120 KB)

    In this paper, we focus on similar image retrieval based on color-content. A two-phase matching strategy is adopted for achieving speed and accuracy of the proposed retrieval: the first phase of matching is intended to produce a candidate image list which are similar to the sample image using the global color histogram; the second phase of matching acts as a filter on the list obtained by the firs... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid hidden Markov model for face recognition

    Publication Year: 2000, Page(s):36 - 40
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (60 KB)

    In this paper, we introduce a hybrid hidden Markov model (HMM) face recognition system. The proposed system contains a low-complexity 2D HMM-based face recognition (LC 2D-HMM FR) module that carries out a complete search in the compressed domain followed by a 1D HMM-based face recognition (1D-HMM FR) module which refines the search based on a candidate list provided by the first module. We also ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Head segmentation and head orientation in 3D space for pose estimation of multiple people

    Publication Year: 2000, Page(s):192 - 196
    Cited by:  Papers (5)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (120 KB)

    We present an algorithm for establishing head orientations of multiple persons in 3D space. Using multiple features from grayscale images (i.e., binary blobs, silhouette contours, and intensity distributions), our algorithm achieves foreground separation, head segmentation, and head-orientation classification, respectively. The information is then combined to form an integrated representation abou... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A spectral-imaging system and algorithms for recovering spectral functions

    Publication Year: 2000, Page(s):278 - 282
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    Knowledge of such spectral functions as the surface-spectral reflectances of objects and the illuminant spectral power distribution is needed for realizing color constancy, accurate color reproduction, and rendering realistic images. This paper describes a spectral-imaging system using a liquid-crystal tunable filter and algorithms for recovering the spectral functions of illuminant and surface re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A simple and efficient method for image segmentation with deformable templates

    Publication Year: 2000, Page(s):31 - 35
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (104 KB)

    A method for the automated segmentation of images containing structures of interest is presented in this work. The method employs a template image for which a segmentation is available. Segmentation of the target image is achieved by deforming the template so as to maximize a similarity measure of the target and template images. The deformations are chosen in accordance with a viscous fluid model.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Seat occupation detection inside vehicles

    Publication Year: 2000, Page(s):187 - 191
    Cited by:  Papers (4)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    In our paper we address the problem of robust seat occupation detection inside vehicles. The approach used consists of four steps: correction of distortions followed by an epipolar rectification of the stereo images, feature extraction, feature-based matching, and the seat occupation detection and verification. The focus in this paper is on the verification of the seat occupation. The step of veri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Edge-retaining asymptotic projections onto convex sets for image interpolation

    Publication Year: 2000, Page(s):78 - 82
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    We propose the concept of asymptotic projections onto convex sets (APOCS) in general and a wavelet (WT)-based, edge-retaining asymptotic POCS (ERAPOCS) algorithm for image interpolation in particular. APOCS differs from POCS in that the projections sequence in one (or more) of the convex sets can enter a desired region rapidly. Like POCS, our proposed algorithm is guaranteed to converge. Our new a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Viewpoint selection - a classifier independent learning approach

    Publication Year: 2000, Page(s):209 - 213
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (112 KB)

    This paper deals with an aspect of active object recognition for improving the classification and localization results by choosing optimal next views at an object. The knowledge of “good” next views at an object is learned automatically and unsupervised from the results of the used classifier. For that purpose methods of reinforcement learning are used in combination with numerical opt... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of determining camera position via Karhunen-Loeve transform

    Publication Year: 2000, Page(s):88 - 92
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (124 KB)

    The Karhunen-Loeve transform (KLT) can be used to compress sets of correlated visual data. Human faces and object recognition are popular areas of current research that use KLT-based methods. The KLT can also be used to compress visual data corresponding to a camera moved translationally and/or rotationally relative to a scene. Positioning of a camera relative to a scene can then be derived accura... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D reconstruction of an urban scene from synthetic fish-eye images

    Publication Year: 2000, Page(s):219 - 223
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    3D scene reconstruction from 2D stereo pairs or sequences has been an interesting issue in computer vision for years. So far, most research has used images acquired by linear low-distortion lenses that can be modeled by pinhole mapping. In recent years, the fisheye lens has received increasing attention and use due to its extremely wide field of view (FOV). However, little has been published on st... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tubular objects network detection from 3D images

    Publication Year: 2000, Page(s):96 - 100
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (100 KB)

    We present an approach to the tree representation of a tubular object network. The full 3D tracking algorithm for a single tubular structure is detailed. Detection of bifurcations by a connectivity approach is then exposed. We show subvoxel accuracy and reliable orientation estimation for the tracking process on synthetic images. Bifurcations are also well detected on a complex synthetic image. Fi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian tree-structured image modeling

    Publication Year: 2000, Page(s):232 - 236
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (196 KB)

    Wavelet-domain hidden Markov models have proven to be useful tools for statistical signal and image processing. The hidden Markov tree (HMT) model captures the key features of the joint statistics of the wavelet coefficients of real-world data. One potential drawback to the HMT framework is the need for computationally expensive iterative training (using the EM algorithm, for example). In this pap... View full abstract»

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