Advances in Pattern Recognition — ICAPR 2001

Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings

  • Sameer Singh
  • Nabeel Murshed
  • Walter Kropatsch
Conference proceedings ICAPR 2001

Part of the Lecture Notes in Computer Science book series (LNCS, volume 2013)

Table of contents

  1. Front Matter
    Pages I-XV


    1. Antanas Verikas, Adas Gelzinis, Kerstin Malmqvist, Marija Bacauskiene
      Pages 40-49
    2. M. De Santo, G. Percannella, C. Sansone, M. Vento
      Pages 50-59
    3. Sameer Singh, Jonathan Fieldsend
      Pages 72-82
    4. Terrillon Jean-Christophe, Mahdad N. Shirazi, Daniel McReynolds, Mohamed Sadek, Yunlong Sheng, Shigeru Akamatsu et al.
      Pages 83-92

    1. Alceu de S. Britto Jr., Robert Sabourin, Flavio Bortolozzi, Ching Y. Suen
      Pages 105-114
    2. Adnan Amin
      Pages 115-126
    3. Alessandro L. Koerich, Robert Sabourin, Ching Y. Suen
      Pages 127-136
    4. Michelangelo Diligenti, Paolo Frasconi, Marco Gori
      Pages 147-156
    5. Victor Kulesh, Kevin Schaffer, Ishwar Sethi, Mark Schwartz
      Pages 157-165

    1. Ming Dong, Ravi Kothari
      Pages 166-175
    2. Nayer M. Wanas, Mohamed S. Kamel
      Pages 176-185
    3. Teófilo E. Campos, Isabelle Bloch, Roberto M. Cesar Jr.
      Pages 186-195

About these proceedings


The paper is organized as follows: In section 2, we describe the no- orientation-discontinuity interfering model based on a Gaussian stochastic model in analyzing the properties of the interfering strokes. In section 3, we describe the improved canny edge detector with an ed- orientation constraint to detect the edges and recover the weak ones of the foreground words and characters; In section 4, we illustrate, discuss and evaluate the experimental results of the proposed method, demonstrating that our algorithm significantly improves the segmentation quality; Section 5 concludes this paper. 2. The norm-orientation-discontinuity interfering stroke model Figure 2 shows three typical samples of original image segments from the original documents and their magnitude of the detected edges respectively. The magnitude of the gradient is converted into the gray level value. The darker the edge is, the larger is the gradient magnitude. It is obvious that the topmost strong edges correspond to foreground edges. It should be noted that, while usually, the foreground writing appears darker than the background image, as shown in sample image Figure 2(a), there are cases where the foreground and background have similar intensities as shown in Figure 2(b), or worst still, the background is more prominent than the foreground as in Figure 2(c). So using only the intensity value is not enough to differentiate the foreground from the background. (a) (b) (c) (d) (e) (f)


3D Augmented Reality Markov Model Pattern recognition Support Vector Machine Textur biometrics character recognition classification document analysis fingerprint handwriting recognition image analysis object recognition topology

Editors and affiliations

  • Sameer Singh
    • 1
  • Nabeel Murshed
    • 2
  • Walter Kropatsch
    • 3
  1. 1.Department of Computer ScienceUniversity of ExeterExeterUK
  2. 2.Computational Intelligence GroupTuiuti University of ParanaCuritibaBrazil
  3. 3.Institute of Computer Aided Automation PRIP-Group 1832Vienna University of TechnologyWienAustria

Bibliographic information

  • DOI
  • Copyright Information Springer-Verlag Berlin Heidelberg 2001
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Springer Book Archive
  • Print ISBN 978-3-540-41767-5
  • Online ISBN 978-3-540-44732-0
  • Series Print ISSN 0302-9743
  • About this book