Non-Uniform Slant Correction for Handwritten Text Line Recognition

Authors:
R. Bertolami;S. Uchida;M. Zimmermann;H. Bunke
Affiliations:
University of Bern, Switzerland;Kyushu University, Fukuoka-shi, Japan;University of Bern, Switzerland;University of Bern, Switzerland
Venue:
ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 01
Year:
2007

Citing 0
Cited 2

Towards robust writer verification by correcting unnatural slant

Pattern Recognition Letters
Arabic handwriting recognition using structural and syntactic pattern attributes

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we apply a novel non-uniform slant correc- tion preprocessing technique to improve the recognition of offline handwritten text lines. The local slant correction is expressed as a global optimisation problem of the sequence of local slant angles. This is different to conventional slant removal techniques that rely on the average slant angle. Ex- periments based on a state-of-the-art handwritten text line recogniser show a significant gain in word level accuracy for the investigated preprocessing methods.