By Topic

Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on

Date 20-20 Aug. 1998

Go

Filter Results

Displaying Results 1 - 25 of 252
  • Proceedings Fourteenth International Conference On Pattern Recognition [front matter]

    Publication Year: 1998, Page(s):i - xxxvi
    Request permission for commercial reuse | PDF file iconPDF (1859 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1998, Page(s):xxxvii - xlvii
    Request permission for commercial reuse | PDF file iconPDF (774 KB)
    Freely Available from IEEE
  • Colour based object tracking

    Publication Year: 1998, Page(s):1442 - 1444 vol.2
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (604 KB)

    A method of detecting and tracking objects using colour is presented. We track objects using a simple colour histogram based technique, which is fast and more robust to occlusion and camera motion than simple "blob" based techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An effective entropic thresholding for ultrasonic images

    Publication Year: 1998, Page(s):1552 - 1554 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (350 KB)

    A new entropy-based thresholding is presented. As a result, a gray level minimizing the difference between the entropy of the object and that of the background will be the desired threshold. Performance of the proposed method has been tested on some ultrasonic images. The results obtained from the method proposed by Kapur et al. (1985) are also given for comparison. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Personal identification based on handwriting

    Publication Year: 1998, Page(s):1761 - 1764 vol.2
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (63 KB)

    Many techniques have been reported for handwriting-based writer identification. Most techniques assume that the written text is fixed (e.g., in signature verification). In this paper we attempt to eliminate this assumption by presenting a novel algorithm for automatic text-independent writer identification. Given that the handwriting of different people can often be visually distinctive, we take a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic selection of illustrations for teaching image processing

    Publication Year: 1998, Page(s):1177 - 1179 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (172 KB)

    We present a system to automatically select images in an image database in order to be used as an illustration of an image processing or analysis process. This question is related to the teleteaching of image processing using already implemented libraries of algorithms, in the context of a teleteaching European project. We first give a Bayesian approach of the problem, with the use of image basis.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face recognition using multiple image view line segments

    Publication Year: 1998, Page(s):1198 - 1200 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (52 KB)

    Describes an image-based face recognition technique using line segments of 2D image views that achieves high generalisation recognition rates for rotations both in and out of the plane, is invariant to scaling, and has reduced execution times. Results show that the algorithm is superior compared with benchmark algorithms and is able to recognise test views in quasi real-time View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmenting by seeking the symmetry axis

    Publication Year: 1998, Page(s):994 - 998 vol.2
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB)

    We introduce a method for segmenting a shape from an image and simultaneously determining its symmetry axis. The symmetry is used to help the segmentation and in turn the segmentation determines the symmetry. The problem is formulated as one of minimizing a goodness of fitness function and Dijkstra's algorithm is used to find the global minimum of the cost function. The results are illustrated on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic generation of initial weights and estimation of hidden units for pattern classification using neural networks

    Publication Year: 1998, Page(s):1568 - 1571 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    This study high lights on the subject of weight initialization in back-propagation feed-forward networks. Training data is analyzed and the notion of critical points is introduced for determining the initial weights and the number of hidden units. The proposed method has been applied to artificial data and the publicly available cancer database. The experimental outcomes indicate that the proposed... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based multi-stage compression of human face images

    Publication Year: 1998, Page(s):1278 - 1280 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    This paper describes a multi-stage compression scheme of human face images. Snakes are employed in localisation of facial features and biorthogonal spline filters are used for the decomposition of segmented and normalised face images. Wavelet coefficients are vector quantized in different number of cascaded stages depending on their contribution to the subjective quality of the image View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Skeleton revision algorithm using maximal circles

    Publication Year: 1998, Page(s):1607 - 1609 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (60 KB)

    Thinning is a fundamental concept of computer processing of line images, and it plays an important role in pattern recognition. Most existing thinning algorithms have the problem to produce distorted skeletons. Some methods to correct the distorted skeleton have been proposed, but non of them produce complete results. In order to solve the problem, we propose an improved thinning algorithm which i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Substroke matching by segmenting and merging for online Korean cursive character recognition

    Publication Year: 1998, Page(s):1110 - 1113 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (84 KB)

    The Korean character is composed of several alphabets in two-dimensional formation and the total number of Korean characters exceeds eleven thousand. Therefore, the previous approaches to Korean cursive characters pay most of their attention to segmenting a character into alphabets accurately. However, it is difficult because the boundaries of alphabets are not apparent in most cases. We propose a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Registration of video to geo-referenced imagery

    Publication Year: 1998, Page(s):1393 - 1400 vol.2
    Cited by:  Papers (29)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (756 KB)

    The ability to locate scenes and objects visible in aerial video imagery with their corresponding locations and coordinates in a reference coordinate system is important in visually-guided navigation, surveillance and monitoring systems. However, a key technical problem of locating objects and scenes in a video with their geo-coordinates needs to be solved in order to ascertain the geo-location of... View full abstract»

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

    Publication Year: 1998, Page(s):1295 - 1297 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB)

    We investigate four different classification methods for document classification: the naive Bayes classifier, nearest neighbor classifier, decision tree classifier, and subspace method. The classifiers were applied to seven-class Yahoo newsgroups individually and in combination. We study three classifier combination approaches: simple voting, dynamic classifier selection, and adaptive classifier c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time and frequency pruning for speaker identification

    Publication Year: 1998, Page(s):1619 - 1621 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    This work is an attempt to refine decisions in speaker identification. A test utterance is divided into multiple time-frequency blocks on which a normalized likelihood score is calculated. Instead of averaging the block-likelihoods along the whole test utterance, some of them are rejected (pruning) and the final score is computed with a limited number of time-frequency blocks. The results obtained... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using centroid covariance in target recognition

    Publication Year: 1998, Page(s):1343 - 1346 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (96 KB)

    An automatic target recognition algorithm for low quality imagery is reported. Compact shaped targets are represented by their 2D silhouettes. Associated with each point on the silhouette, there is a direction roughly perpendicular to the local segment of the silhouette. The location of each silhouette point is assumed to be perturbed along that direction. A statistical technique is used to estima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cut detection technique from MPEG compressed video using likelihood ratio test

    Publication Year: 1998, Page(s):1476 - 1480 vol.2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    A cut detection technique using a likelihood ratio test for MPEG compressed video sequences is proposed. Automatic cut detection techniques are essential techniques to analyze video content. The conventional techniques calculate the similarities of two successive frames and determine cut points by comparing the similarities with a given threshold value; the threshold value is determined heuristica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Memory-based self-localization using omnidirectional images

    Publication Year: 1998, Page(s):1799 - 1803 vol.2
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    This paper proposes a new self-localization method using an omnidirectional image sensor which can observe a surrounding environment with 360-degree of view. The method extracts information which is identical for the position of a sensor and invariant against the rotation of the sensor by generating an autocorrelation image from an observed omnidirectional image. The location of the sensor is esti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning multidimensional signal processing

    Publication Year: 1998, Page(s):1416 - 1420 vol.2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (388 KB)

    This paper presents our general strategy for designing learning machines as well as a number of particular designs. The search for methods allowing a sufficient level of adaptivity are based on two main principles: 1) simple adaptive local models; and 2) adaptive model distribution. Particularly important concepts in our work is mutual information and canonical correlation. Examples are given on l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-scale image analysis for detection of characteristic component figure shapes and sizes

    Publication Year: 1998, Page(s):1470 - 1472 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (192 KB)

    A method which detects the characteristic shapes and sizes of image structures is proposed. The method first blurs an image by Gaussian filters with various scales. Then, at every scale, principal curvatures of the image gray-level profile are calculated for every position. As the scale changes, the principal curvatures change. We detect the inherent shapes and sizes of the image structures by cha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture classification using wavelet decomposition with Markov random field models

    Publication Year: 1998, Page(s):1613 - 1615 vol.2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    We present a new scheme to classify different textures. In the past years, wavelet decomposition has been used in texture classification. The usual features of classification are energy and entropy. In this paper, we propose a scheme to use wavelet decomposition with Markov random field models, the parameters of each Markov random field models are used as features in texture classification. Thus w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature extraction method for palmprint considering elimination of creases

    Publication Year: 1998, Page(s):1849 - 1854 vol.2
    Cited by:  Papers (7)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    A new method of extracting palmprint features is presented in this report. Since palmprint images have many creases which are organized like ridges, ordinary fingerprint feature extraction algorithms are unable to extract ridges. Consequently, the goal of this research is to construct a new feature extraction method which can extract ridges under these conditions. At first, the original palmprint ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust extraction of characters from color scene image using mathematical morphology

    Publication Year: 1998, Page(s):1002 - 1004 vol.2
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    Current character extraction systems for scene images are not robust for most real-world applications. In contrast, the system present here achieves robust performance by using morphological segmentation. This paper describes a new morphological segmentation algorithm-differential top-hats (DTT). In, addition, a complete system for extraction of characters from color scene images is presented. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • E-mail signature block analysis

    Publication Year: 1998, Page(s):1153 - 1156 vol.2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (664 KB)

    The signature block is a common structured component found in e-mail messages. Accurate identification and analysis of signature blocks are important in many multimedia messaging and information retrieval applications such as e-mail text-to-speech rendering. Traditional text analysis methods designed to deal with sequential text cannot handle 2D structures, while the highly unconstrained nature of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of urban scenes from aerial stereo imagery

    Publication Year: 1998, Page(s):1405 - 1407 vol.2
    Cited by:  Papers (1)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (156 KB)

    Presents a focusing strategy for the 3-D reconstruction of urban scenes from aerial stereo pairs. It consists in segmenting the scene into above-ground objects (buildings or vegetation), and it relies on 3-D and radiometric analyses. The classification is able to cope with extended above-ground, adjacent objects, slopes, and it is robust to image and scene variability View full abstract»

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