By Topic

Pattern Recognition, 2002. Proceedings. 16th International Conference on

Date 11-15 Aug. 2002

Go

Filter Results

Displaying Results 1 - 25 of 95
  • Classification using a hierarchical Bayesian approach

    Publication Year: 2002 , Page(s): 103 - 106 vol.4
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (437 KB) |  | HTML iconHTML  

    A key problem faced by classifiers is coping with styles not represented in the training set. We present an application of hierarchical Bayesian methods to the problem of recognizing degraded printed characters in a variety of fonts. The proposed method works by using training data of various styles and classes to compute prior distributions on the parameters for the class conditional distribution... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative study of centroid-based, neighborhood-based and statistical approaches for effective document categorization

    Publication Year: 2002 , Page(s): 235 - 238 vol.4
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (464 KB) |  | HTML iconHTML  

    Associating documents to relevant categories is critical for effective document retrieval. Here, we compare the well-known k-nearest neighborhood (kNN) algorithm, the centroid-based classifier and the highest average similarity over retrieved documents (HASRD) algorithm, for effective document categorization. We use various measures such as the micro and macro F1 values to evaluate their performan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings 16th International Conference on Pattern Recognition

    Publication Year: 2002 , Page(s): iii - xi
    Save to Project icon | Request Permissions | PDF file iconPDF (333 KB)  
    Freely Available from IEEE
  • List of referees

    Publication Year: 2002 , Page(s): xv - xvii
    Save to Project icon | Request Permissions | PDF file iconPDF (132 KB)  
    Freely Available from IEEE
  • Author index

    Publication Year: 2002 , Page(s): 397 - 418
    Save to Project icon | Request Permissions | PDF file iconPDF (1066 KB)  
    Freely Available from IEEE
  • Space-time invariants and video motion extraction from arbitrary viewpoints

    Publication Year: 2002 , Page(s): 56 - 59 vol.4
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (492 KB) |  | HTML iconHTML  

    The recognition of motions is very important for understanding dynamic actions and extracting events from video sequences. We propose invariants on object motions, which can be extracted from image sequences, and are invariant even if the motions are viewed from arbitrary viewpoints. We call them space-time invariants since they are defined under space-time projections. We show that these invarian... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mixed Bayesian networks with auxiliary variables for automatic speech recognition

    Publication Year: 2002 , Page(s): 293 - 296 vol.4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (409 KB) |  | HTML iconHTML  

    In standard automatic speech recognition (ASR), hidden Markov models (HMMs) calculate their emission probabilities by an artificial neural network (ANN) or a Gaussian distribution conditioned only upon the hidden state variable. Stephenson et al. (2001) showed the benefit of conditioning the emission distributions also upon a discrete auxiliary variable, which is observed in training and hidden in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time implementation of an optical flow algorithm

    Publication Year: 2002 , Page(s): 247 - 250 vol.4
    Cited by:  Papers (16)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (455 KB) |  | HTML iconHTML  

    This paper presents the implementation of an optical flow algorithm on a pipeline image processor The overall optical flow computation method is presented and evaluated on a common set of image sequences. Results are compared to other implementations according to two different error measures. Due to its deterministic architecture, this implementation achieves very low computation delays that allow... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A large scale clustering scheme for kernel K-Means

    Publication Year: 2002 , Page(s): 289 - 292 vol.4
    Cited by:  Papers (16)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (430 KB) |  | HTML iconHTML  

    Kernel functions can be viewed as a non-linear transformation that increases the separability of the input data by mapping them to a new high dimensional space. The incorporation of kernel functions enables the K-Means algorithm to explore the inherent data pattern in the new space. However, the previous applications of the kernel K-Means algorithm are confined to small corpora due to its expensiv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning quadratic discriminant function for handwritten character classification

    Publication Year: 2002 , Page(s): 44 - 47 vol.4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (413 KB) |  | HTML iconHTML  

    For handwriting recognition integrating segmentation and classification, the underlying classifier is desired to give both high accuracy and resistance to outliers. In a previous evaluation study, the modified quadratic discriminant function (MQDF) proposed by Kimura et al. (1987) was shown to be superior in outlier rejection but inferior in classification accuracy as compared to neural classifier... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative analysis of face recognition performance with visible and thermal infrared imagery

    Publication Year: 2002 , Page(s): 217 - 222 vol.4
    Cited by:  Papers (34)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (657 KB) |  | HTML iconHTML  

    We present a comprehensive performance analysis of multiple appearance-based face recognition methodologies, on visible and thermal infrared imagery. We compare algorithms within and between modalities in terms of recognition performance, false alarm rates and requirements to achieve specified performance levels. The effect of illumination conditions on recognition performance is emphasized, as it... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A windowed weighted approach for approximate cyclic string matching

    Publication Year: 2002 , Page(s): 188 - 191 vol.4
    Cited by:  Papers (1)  |  Patents (12)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (437 KB) |  | HTML iconHTML  

    A method for measuring dissimilarities between cyclic strings is introduced. It computes a weighted mean between two (lower and upper) bounds of the exact cyclic edit distance, which are founded on a window-constrained edit graph related to the strings involved. Weights are the ones which minimize the sum of squared relative errors of the weighted solution with respect to exact values, on a traini... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local affine frames for wide-baseline stereo

    Publication Year: 2002 , Page(s): 363 - 366 vol.4
    Cited by:  Papers (19)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (508 KB) |  | HTML iconHTML  

    A novel procedure for establishing wide-baseline correspondence is introduced. Tentative correspondences are established by matching photometrically normalised colour measurements represented in a local affine frame. The affine frames are obtained by a number of affine invariant constructions on robustly detected, maximally stable extremal regions of data-dependent shape. Several processes for loc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure from motion from three affine views

    Publication Year: 2002 , Page(s): 1 - 6 vol.4
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (647 KB) |  | HTML iconHTML  

    We describe a new method for structure from motion (SFM) from three affine views. The central idea of the method is to explore the intrinsic three-view properties instead of previous two-view ones. The first key observation is that an affine camera is indeed essentially a one-dimensional projective camera operating on the plane at infinity : we prove that the essential motion-relative camera orien... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative evaluation of length estimators

    Publication Year: 2002 , Page(s): 330 - 334 vol.4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (483 KB) |  | HTML iconHTML  

    The paper compares previously published length estimators having digitized curves as input. The evaluation uses multigrid convergence (theoretical results and measured speed of convergence) and further measures as criteria. The paper also suggests a new gradient-based method for length estimation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstructing mirror symmetric scenes from a single view using 2-view stereo geometry

    Publication Year: 2002 , Page(s): 12 - 16 vol.4
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (499 KB) |  | HTML iconHTML  

    We address the problem of 3D reconstruction from a single perspective view of a mirror symmetric scene. We establish the fundamental result that it is geometrically equivalent to observing the scene with two cameras, the cameras being symmetrical with respect to the unknown 3D symmetry plane. All traditional tools of classical 2-view stereo can then be applied, and the concepts of fundamental/esse... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D reconstruction from co-registered orthographic and perspective images: theoretical framework and applications

    Publication Year: 2002 , Page(s): 21 - 26 vol.4
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (719 KB) |  | HTML iconHTML  

    In this paper a complete framework for 3D reconstruction is proposed which is based on co-registered technical drawings and images. Instead of gaining 3D information from multiple perspective images of a scene, we use only a single perspective image which is augmented by a registered 2D drawing of the scene. By superimposing images with drawings a new type of document is created which we call co-r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic neural networks supporting multi-class relevance feedback in region-based image retrieval

    Publication Year: 2002 , Page(s): 138 - 141 vol.4
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (546 KB) |  | HTML iconHTML  

    There are several relevance feedback algorithms available, some algorithms use ad-hoc heuristics or assume that feature vectors are independent regardless of their correlation. In this paper, we propose a new relevance feedback algorithm using probabilistic neural networks (PNN) supporting multi-class learning. In our approach, there is no need to assume that feature vectors are independent and it... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quantitative color optical flow

    Publication Year: 2002 , Page(s): 251 - 255 vol.4
    Cited by:  Papers (19)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (904 KB) |  | HTML iconHTML  

    We perform a qualitative and quantitative analysis of various multi-frame color optical flow methods for synthetic and real panning and zooming image sequences. We show that optical flow accuracy improvement can be slightly improved if color images are available instead of gray value or saturation images. We show the usefulness of a directional regularization constraint for computing optical flow ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum likelihood structure and motion estimation integrated over time

    Publication Year: 2002 , Page(s): 260 - 263 vol.4
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (418 KB) |  | HTML iconHTML  

    Least squares minimization of the differential epipolar constraint is a fast and efficient technique to estimate structure and motion for pair of views. Previous work in this area showed how unbiased and consistent estimates could be obtained minimizing the squared errors. However it implicitly assumes that the errors along the x and y directions are identical and uncorrelated. This is rarely the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear robust velocity estimation of vehicles from a snowfall traffic scene

    Publication Year: 2002 , Page(s): 60 - 63 vol.4
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (510 KB) |  | HTML iconHTML  

    Discusses a robust velocity estimation method for moving vehicles in road traffic image sequences under snowy and misty weather conditions. In such environments, it is difficult to detect the velocity of vehicles because of discontinuities, occlusions, noise, and brightness variations. It should also be noted that falling snow results in indefinite shapes and motion, which occludes the region of i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tetrahedron mapping of points from n-space to three-space

    Publication Year: 2002 , Page(s): 343 - 346 vol.4
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (462 KB) |  | HTML iconHTML  

    We extend the triangulation method of Lee et al. (1977) and present a tetrahedron method for the sequential mapping of points in high-dimensional space into three-space. The three-space preserves distances among nodes of a tetrahedron. Whenever a new point is mapped, its distances to three points previously mapped are exactly preserved. Among these three points, one can be chosen as the point conn... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo tracking using ICP and normal flow constraint

    Publication Year: 2002 , Page(s): 367 - 372 vol.4
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (537 KB) |  | HTML iconHTML  

    This paper presents a new approach for 3D view registration of stereo images. We introduce a hybrid error function which combines constraints from the ICP (iterative closest point) algorithm and normal flow constraint. This new technique is more precise for small movements and noisy depth than ICP alone, and more robust for large movements than the normal flow constraint alone. Finally, we present... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An objective distortion measure for binary document images based on human visual perception

    Publication Year: 2002 , Page(s): 239 - 242 vol.4
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (436 KB) |  | HTML iconHTML  

    As we are moving to a digital world, digital document image processing is receiving more and more attention. Digital document images are essentially binary images. In applications related to binary document images, such as data hiding and watermarking in binary images, distortion may be present and it is necessary to measure the distortion for performance comparison. However traditional objective ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusion of range and visual data for the extraction of scene structure information

    Publication Year: 2002 , Page(s): 7 - 11 vol.4
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (577 KB) |  | HTML iconHTML  

    In this paper a method for inferring 3D structure information based on both range and visual data is proposed. Data fusion is achieved by validating assumptions formed according to 2D range scans of the environment, through the exploitation of visual information. The proposed method is readily applicable to robot navigation tasks providing significant advantages over existing methods. View full abstract»

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