A soft-decision approach for symbol segmentation within handwritten mathematical expressions

Author

Lehmberg, Stefan ; Winkler, Hans-Jìrgen ; Lang, Manfred

Author_Institution

Inst. for Human-Machine-Commun., Tech. Univ. Munchen, Germany

Volume

6

fYear

1996

fDate

7-10 May 1996

Firstpage

3434

Abstract

A soft-decision approach for symbol segmentation within on-line sampled handwritten mathematical expressions is presented. Based on stroke-specific features as well as geometrical features between the strokes a symbol hypotheses net is generated. For assistance additional knowledge obtained by a symbol prerecognition stage is used. The results achieved by the segmentation and prerecognition experiments indicate the performance of our approach

Keywords

character recognition; feature extraction; handwriting recognition; image recognition; image sampling; image segmentation; neural nets; geometrical features; neural networks; online sampled handwritten mathematical expressions; performance; prerecognition experiments; segmentation experiments; soft-decision approach; stroke specific features; symbol hypotheses net; symbol prerecognition; symbol segmentation; Handwriting recognition; Image segmentation; Text recognition; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.550766

Filename

550766