By Topic

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

Date 2002

Go

Filter Results

Displaying Results 1 - 25 of 95
  • A comparative study of centroid-based, neighborhood-based and statistical approaches for effective document categorization

    Publication Year: 2002, Page(s):235 - 238 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | 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.
  • Classification using a hierarchical Bayesian approach

    Publication Year: 2002, Page(s):103 - 106 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | 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.
  • Proceedings 16th International Conference on Pattern Recognition

    Publication Year: 2002, Page(s):iii - xi
    Request permission for commercial reuse | PDF file iconPDF (333 KB)
    Freely Available from IEEE
  • List of referees

    Publication Year: 2002, Page(s):xv - xvii
    Request permission for commercial reuse | PDF file iconPDF (132 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 2002, Page(s):397 - 418
    Request permission for commercial reuse | PDF file iconPDF (1066 KB)
    Freely Available from IEEE
  • 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)
    Request permission for commercial reuse | 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.
  • Curve morphing by weighted mean of strings

    Publication Year: 2002, Page(s):192 - 195 vol.4
    Cited by:  Papers (79)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (409 KB) | HTML iconHTML

    We propose an approach to curve morphing. We represent curves by strings, i.e. sequences of symbols. The curve morphing problem is formulated as that of, computing a weighted mean of two strings, which is then solved by a corresponding algorithm. Although only 2D curves are used in our experiments, the approach is applicable to curves in any dimension. Curve morphing has interesting applications i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmenting actions in velocity curve space

    Publication Year: 2002, Page(s):170 - 175 vol.4
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (693 KB) | HTML iconHTML

    Reliable segmentation of actions performed by objects, is critical to the understanding of semantic content in a video. Deciding which portion of object motion sequence is a distinct action unit, however, is often difficult, even for humans. We seem to hierarchically compose actions by noting characteristic changes in the nature of motion. This paper present an action segmentation algorithm that m... 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 (20)
    Request permission for commercial reuse | 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.
  • Structure from motion from three affine views

    Publication Year: 2002, Page(s):1 - 6 vol.4
    Request permission for commercial reuse | 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.
  • Head pose estimation using view based eigenspaces

    Publication Year: 2002, Page(s):302 - 305 vol.4
    Cited by:  Papers (16)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (402 KB) | HTML iconHTML

    View based eigenspaces can improve the performance of face recognition algorithms. In this work, we demonstrate their use in head pose estimation from head and shoulders video sequences. Our method compares the projected energies of the test image in multiple eigenspaces. We also demonstrate that very few eigenspaces are necessary for a rough estimate of head pose. The method is robust and computa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Featureless 6 DOF pose refinement from stereo images

    Publication Year: 2002, Page(s):17 - 20 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (475 KB) | HTML iconHTML

    We present a pose estimation method from an initial unreliable guess using calibrated stereo images. The approach does not rely on a priori known salient features on the surface. The stereo images are brought in congruence without computing a disparity map like in standard stereo algorithms. Instead, the pose parameters of the object are varied to match the stereo images on the known surface shape... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust affine motion estimation in joint image space using tensor voting

    Publication Year: 2002, Page(s):256 - 259 vol.4
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (515 KB) | HTML iconHTML

    Robustness of parameter estimation relies on discriminating inliers from outliers within the set of correspondences. In this paper, we present a method using tensor voting to eliminate outliers and estimating affine transformation parameters directly from covariance matrix of selected inliers without additional parameter estimation processing. Our approach is based on the representation of the cor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast near-optimal algorithm for approximation of polygonal curves

    Publication Year: 2002, Page(s):335 - 338 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (402 KB) | HTML iconHTML

    Approximation of polygonal curves can be solved by dynamic programming. These methods provide an optimal solution but are slow for a large number of vertices. We propose a new optimization approach based on dynamic programming with a reduced-search in the state space. The proposed algorithm is simple, fast, and has low space complexity. The time and quality trade-off can be controlled by selecting... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new algorithm for inexact graph matching

    Publication Year: 2002, Page(s):180 - 183 vol.4
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (446 KB) | HTML iconHTML

    The graph is an essential data structure for representing relational information. When graphs are used to represent objects, comparing objects amounts to graph matching. Inexact graph matching is the process of finding the best possible matching between two graphs when exact matching is impossible. We propose a new algorithm for the inexact matching problem. The new algorithm decomposes the matchi... 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 (5)
    Request permission for commercial reuse | 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.
  • Local affine frames for wide-baseline stereo

    Publication Year: 2002, Page(s):363 - 366 vol.4
    Cited by:  Papers (22)
    Request permission for commercial reuse | 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.
  • Registering panoramic range data and omnidirectional color image based on edge histograms

    Publication Year: 2002, Page(s):355 - 358 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (547 KB) | HTML iconHTML

    In this paper we propose a robust method to register a panoramic range data obtained by a panoramic laser range finder and an omnidirectional image acquired by a stereo omnidirectional system (SOS), by matching the horizontal and vertical edge histograms of the two images. The proposed method first estimates the relative horizontal rotation angle by matching the vertical edge histograms. Next, for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A string length predictor to control the level building of HMMs for handwritten numeral recognition

    Publication Year: 2002, Page(s):31 - 34 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (439 KB) | HTML iconHTML

    In this paper a two-stage HMM-based method for recognizing handwritten numeral strings is extended to work with handwritten numeral strings of unknown length. We have proposed a Bayesian-based string length predictor (SLP) to estimate the number of digits in a string taking into account its width in pixels. The top 3 decisions of the SLP module are used to control the maximum number of levels to b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion retrieval by temporal slices analysis

    Publication Year: 2002, Page(s):64 - 67 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (435 KB) | HTML iconHTML

    We investigate video shots retrieval based on the analysis of temporal slice images. Temporal slices are a set of 2D images extracted along the time dimension of image sequences. They encode a rich set of motion clues for shot similarity measure. Because motion is depicted as texture orientation in temporal slices, we utilize various texture features such as tensor histogram, Gabor feature, and th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content based image retrieval using optimum Peano scan

    Publication Year: 2002, Page(s):130 - 133 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (602 KB) | HTML iconHTML

    We present a new technique for content based image retrieval where feature vector to be matched is very much specific to the query image. A particular Peano scan which is optimal in encoding the query image is used to convert the scanning pattern of all database images. Features are derived from these scan converted images to calculate the similarity measure. As the features being query specific, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color-based face detection using skin locus model and hierarchical filtering

    Publication Year: 2002, Page(s):196 - 200 vol.4
    Cited by:  Papers (9)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (483 KB) | HTML iconHTML

    Introduces an architecture for face detection in color images. Based on skin locus and successive detectors, the method allows high efficiency, under drastically varying illumination conditions. While most color-based approaches work only if the camera was calibrated and detect faces if the features (eyes, mouth, eyebrows...) are visible and detectable, our system detects faces even when these fea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An original multi-scale algorithm to binarize images

    Publication Year: 2002, Page(s):322 - 325 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (426 KB) | HTML iconHTML

    An original approach to binarize gray level images is proposed. A multi-scale algorithm based on a statistical test of homogeneity decides if a region belongs to the background or not. At each iteration the image is smoothed with a nonlinear filter in order to remove the noise. Stable regions in scale space are used to automatically find a threshold from the intensity histogram. 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)
    Request permission for commercial reuse | 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.
  • Motion-based obstacle detection and tracking for car driving assistance

    Publication Year: 2002, Page(s):74 - 77 vol.4
    Cited by:  Papers (15)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (743 KB) | HTML iconHTML

    The paper is concerned with the detection and tracking of obstacles from a camera mounted on a vehicle with a view to driver assistance. To achieve this goal, we have designed a technique entirely based on image motion analysis. We perform the robust estimation of the dominant image motion assumed to be due to the camera motion. Then by considering the outliers to the estimated dominant motion, we... View full abstract»

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