Abstract
In the framework of handwritten word recognition, the use of characters extracted from words instead of written in isolation, is essential to train recognizers. We propose a segmentation method which relies on anchor points such as the ascenders or the descenders, but also on certain kinds of loops. We do not use a manually segmented prototype set to initialize our incremental learning process, but instead we use an a priori knowledge about the alphabet characters. This knowledge is introduced as the encoding of the descending movements of the pen and of loops. From a set of words written by the same writer, we evaluate the different possible segmentations for each word and use the ones superior to a certain threshold. In the beginning this threshold is rather high. At each step of the segmentation of the words, its value decreases in order to register new prototypes. The characters already accepted are used in the next steps. The confidence rate is maximum for 3 steps.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
C.J.C. Burges and al. Shortest path segmentation: A method for training a neural network to recognize character strings. In IJCNN, pages 165–172, vol 3, Cambridge, Ma, 1992.
L. Duneau and B. Dorizzi. Incremental building of an allograph lexicon. In Advances in handwriting & drawing: a multidisciplinary approach, pages 39–63. C. Faure. Reuss P., Lorette G. and Vinter A., 1994.
Annick Leroy. Progressive lexicon reduction for on-line handwriting. In IWFHR 5, Colchester, UK, 1996.
H.L. Teulings and L. Schomaker. Unsupervised learning of prototype allographs in cursive script recognition. In From Pixels to Features III, pages 61–73. S. Impedovo and J.C. Simon, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leroy, A. (1997). Unsupervised learning of character prototypes. In: Murshed, N.A., Bortolozzi, F. (eds) Advances in Document Image Analysis. BSDIA 1997. Lecture Notes in Computer Science, vol 1339. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63791-5_18
Download citation
DOI: https://doi.org/10.1007/3-540-63791-5_18
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63791-2
Online ISBN: 978-3-540-69646-9
eBook Packages: Springer Book Archive