Handwritten Character Segmentation Using Transformation-Based Learning

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by E. Kavallieratou Articles by E. Stamatatos Articles by N. Fakotakis Articles by G. Kokkinakis

15th International Conference on Pattern Recognition (ICPR'00) - Volume 2

Barcelona, Spain

September 03-September 08

ISBN: 0-7695-0750-6

	ASCII Text	x
	E. Kavallieratou, E. Stamatatos, N. Fakotakis, G. Kokkinakis, "Handwritten Character Segmentation Using Transformation-Based Learning," Pattern Recognition, International Conference on, vol. 2, pp. 2634, 15th International Conference on Pattern Recognition (ICPR'00) - Volume 2, 2000.

	BibTex	x
	@article{ 10.1109/ICPR.2000.906155, author = {E. Kavallieratou and E. Stamatatos and N. Fakotakis and G. Kokkinakis}, title = {Handwritten Character Segmentation Using Transformation-Based Learning}, journal ={Pattern Recognition, International Conference on}, volume = {2}, year = {2000}, isbn = {0-7695-0750-6}, pages = {2634}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2000.906155}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Pattern Recognition, International Conference on TI - Handwritten Character Segmentation Using Transformation-Based Learning SN - 0-7695-0750-6 SP EP A1 - E. Kavallieratou, A1 - E. Stamatatos, A1 - N. Fakotakis, A1 - G. Kokkinakis, PY - 2000 VL - 2 JA - Pattern Recognition, International Conference on ER -

E. Kavallieratou, University of Patras

E. Stamatatos, University of Patras

N. Fakotakis, University of Patras

G. Kokkinakis, University of Patras

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPR.2000.906155

This paper presents a character segmentation algorithm for unconstrained cursive handwritten text. The transformation-based learning method and a simplified variation of it are used in order to extract automatically rules that detect the segment boundaries. Comparative experimental results are given for a collection of multi-writer handwritten words. The achieved accuracy in detecting segment boundaries exceeds 82%. Moreover, limited training data can provide very satisfactory results.

Citation:

E. Kavallieratou, E. Stamatatos, N. Fakotakis, G. Kokkinakis, "Handwritten Character Segmentation Using Transformation-Based Learning," icpr, vol. 2, pp.2634, 15th International Conference on Pattern Recognition (ICPR'00) - Volume 2, 2000

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.