Document Type

Journal Article

Department/Unit

Department of Computer Science

Title

Bidirectional deformable matching with application to handwritten character extraction

Language

English

Abstract

To achieve integrated segmentation and recognition in complex scenes, the model-based approach has widely been accepted as a promising paradigm. However, the performance is still far from satisfactory when the target object is highly deformed and the level of outlier contamination is high. In this paper, we first describe two Bayesian frameworks, one for classifying input patterns and another for detecting target patterns in complex scenes using deformable models. Then, we show that the two frameworks are similar to the forward-reverse setting of Hausdorff matching and that their matching and discriminating properties are complementary to each other. By properly combining the two frameworks, we propose a new matching scheme called bidirectional matching. This combined approach inherits the advantages of the two Bayesian frameworks. In particular, we have obtained encouraging empirical results on shape-based pattern extraction, using a subset of the CEDAR handwriting database containing handwritten words of highly varying shape.

Keywords

Deformable models, Shape, Stereo vision, Layout, Application software, Bayesian methods, Computer vision, Data mining, Contamination, Image segmentation

Publication Date

8-2002

Source Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volume

24

Issue

8

Start Page

1133

End Page

1139

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Peer Reviewed

1

Funder

The authors would like to thank the Hong Kong Research Grants Council (RGC) for supporting this research through two research grants (RGC 746/96E and RGC 6081/97E).

DOI

10.1109/TPAMI.2002.1024135

Link to Publisher's Edition

http://dx.doi.org/10.1109/TPAMI.2002.1024135

ISSN (print)

01628828

ISSN (electronic)

19393539

This document is currently not available here.

Share

COinS