On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network

Jong Oh, Davi Geiger

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose an on-line handwriting recognition approach that integrates local bottom-up constructs with a global top-down measure into a modular recognition engine. The bottom-up process uses local point features for hypothesizing character segmentations and the top-down part performs shape matching for evaluating the segmentations. The shape comparison, called Fisher segmental matching, is based on Fisher's linear discriminant analysis. Along with an efficient ligature modeling, the segmentations and their matching scores are integrated into a recognition engine termed Hypotheses Propagation Network, which runs a variant of topological sort algorithm of graph search. The result is a system that is more shape-oriented, less dependent on local and temporal features, modular in construction and has a rich range of opportunities for further extensions. Our system currently performs at 95% of recognition rate on cursive scripts with a 460-words dictionary.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages343-348
Number of pages6
Volume2
StatePublished - 2000
EventCVPR '2000: IEEE Conference on Computer Vision and Pattern Recognition - Hilton Head Island, SC, USA
Duration: Jun 13 2000Jun 15 2000

Other

OtherCVPR '2000: IEEE Conference on Computer Vision and Pattern Recognition
CityHilton Head Island, SC, USA
Period6/13/006/15/00

Fingerprint

Engines
Discriminant analysis
Glossaries

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering

Cite this

Oh, J., & Geiger, D. (2000). On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2, pp. 343-348)

On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network. / Oh, Jong; Geiger, Davi.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2 2000. p. 343-348.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Oh, J & Geiger, D 2000, On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 2, pp. 343-348, CVPR '2000: IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, SC, USA, 6/13/00.
Oh J, Geiger D. On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2. 2000. p. 343-348
Oh, Jong ; Geiger, Davi. / On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2 2000. pp. 343-348
@inproceedings{f1390dcef067466c9ddf71e137e18d94,
title = "On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network",
abstract = "We propose an on-line handwriting recognition approach that integrates local bottom-up constructs with a global top-down measure into a modular recognition engine. The bottom-up process uses local point features for hypothesizing character segmentations and the top-down part performs shape matching for evaluating the segmentations. The shape comparison, called Fisher segmental matching, is based on Fisher's linear discriminant analysis. Along with an efficient ligature modeling, the segmentations and their matching scores are integrated into a recognition engine termed Hypotheses Propagation Network, which runs a variant of topological sort algorithm of graph search. The result is a system that is more shape-oriented, less dependent on local and temporal features, modular in construction and has a rich range of opportunities for further extensions. Our system currently performs at 95{\%} of recognition rate on cursive scripts with a 460-words dictionary.",
author = "Jong Oh and Davi Geiger",
year = "2000",
language = "English (US)",
volume = "2",
pages = "343--348",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - On-line handwriting recognition system using fisher segmental matching and Hypotheses Propagation Network

AU - Oh, Jong

AU - Geiger, Davi

PY - 2000

Y1 - 2000

N2 - We propose an on-line handwriting recognition approach that integrates local bottom-up constructs with a global top-down measure into a modular recognition engine. The bottom-up process uses local point features for hypothesizing character segmentations and the top-down part performs shape matching for evaluating the segmentations. The shape comparison, called Fisher segmental matching, is based on Fisher's linear discriminant analysis. Along with an efficient ligature modeling, the segmentations and their matching scores are integrated into a recognition engine termed Hypotheses Propagation Network, which runs a variant of topological sort algorithm of graph search. The result is a system that is more shape-oriented, less dependent on local and temporal features, modular in construction and has a rich range of opportunities for further extensions. Our system currently performs at 95% of recognition rate on cursive scripts with a 460-words dictionary.

AB - We propose an on-line handwriting recognition approach that integrates local bottom-up constructs with a global top-down measure into a modular recognition engine. The bottom-up process uses local point features for hypothesizing character segmentations and the top-down part performs shape matching for evaluating the segmentations. The shape comparison, called Fisher segmental matching, is based on Fisher's linear discriminant analysis. Along with an efficient ligature modeling, the segmentations and their matching scores are integrated into a recognition engine termed Hypotheses Propagation Network, which runs a variant of topological sort algorithm of graph search. The result is a system that is more shape-oriented, less dependent on local and temporal features, modular in construction and has a rich range of opportunities for further extensions. Our system currently performs at 95% of recognition rate on cursive scripts with a 460-words dictionary.

UR - http://www.scopus.com/inward/record.url?scp=0033714463&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033714463&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033714463

VL - 2

SP - 343

EP - 348

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -