Improvement of matching and evaluation in handwritten numeral recognition using flexible standard patterns

Author

MURAMATSU, Hirokazu ; KOBAYASHI, Takashi ; Sugiyama, Takahiro ; Abe, Keiichi

Author_Institution

Graduate Sch. of Inf., Shizuoka Univ., Hamamatsu, Japan

fYear

2003

fDate

3-6 Aug. 2003

Firstpage

273

Abstract

The purpose of this study is to develop a flexible matching method for recognizing handwritten numerals based on the statistics of shapes and structures learned from learning samples. In the recognition method we reported before, there were problems in matching of the feature points and evaluation of matching. To solve them, we propose a new matching method supplementing contour orientations with convex/concave information and a new evaluation method considering the structure of strokes. With these improvements the recognition rate rose to 96.0% from the earlier figure 91.9%. We also made a recognition experiment on samples from the ETL-1 database and obtained the recognition rate 95.2%.

Keywords

feature extraction; handwritten character recognition; image matching; learning by example; concave information; contour orientation; convex information; flexible matching method; flexible standard pattern; handwritten numeral recognition; matching evaluation; shape statistics; stroke structure; structure statistics; Character recognition; Feature extraction; Handwriting recognition; Humans; Measurement standards; Pattern matching; Pattern recognition; Shape; Standards development; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on

Print_ISBN

0-7695-1960-1

Type

conf

DOI

10.1109/ICDAR.2003.1227672

Filename

1227672