Abstract
This paper describes the normalisation and preprocessing operations which have been implemented as the preprocessing stages of a complete off-line handwriting recognition system based on recurrent networks. These operations remove shears, rotations and scaling from words, and estimate the position of the important base-lines. The paper also describes the methods used to encode the data and to determine the presence of writing features which are of benefit in the recognition processes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
R.M. Božinović and S.N. Srihari. Off-line cursive word recognition. IEEE PAMI, 11(1):68–83, January 1989.
E.R. Davies. Machine Vision: Theory, algorithms, practicalities. Microelectrics and signal processing Number 9. London Academic, 1990.
Andreas Lanitis. Applications of point distribution models in handwritten optical character recognition and face recognition. Transfer report, Dept. of Medical Biophysics, University of Manchester, 1992.
Tony Robinson and Frank Fallside. A recurrent error propagation network speech recognition system. Computer Speech and Language, 5:259–274, 1991.
A.W. Senior and F. Fallside. Using constrained snakes for feature spotting in off-line cursive script. In International Conference on Document Analysis and Recognition 93, 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Senior, A.W. (1994). Normalisation and Preprocessing for a Recurrent Network Off-line Handwriting Recognition System. In: Impedovo, S. (eds) Fundamentals in Handwriting Recognition. NATO ASI Series, vol 124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78646-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-78646-4_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-78648-8
Online ISBN: 978-3-642-78646-4
eBook Packages: Springer Book Archive