Distance-based classification of handwritten symbols

Authors:
Oleg Golubitsky;Stephen M. Watt
Affiliations:
University of Western Ontario, N6A5B7, London, ON, Canada;University of Western Ontario, N6A5B7, London, ON, Canada
Venue:
International Journal on Document Analysis and Recognition - Special Issue DRR09
Year:
2010

Citing 0
Cited 6

Toward affine recognition of handwritten mathematical characters

DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
Polynomial approximation in handwriting recognition

Proceedings of the 2011 International Workshop on Symbolic-Numeric Computation
A streaming digital ink framework for multi-party collaboration

CICM'12 Proceedings of the 11th international conference on Intelligent Computer Mathematics
Writing on clouds

CICM'12 Proceedings of the 11th international conference on Intelligent Computer Mathematics
Determining points on handwritten mathematical symbols

CICM'13 Proceedings of the 2013 international conference on Intelligent Computer Mathematics
Legendre polynomials based feature extraction for online signature verification. Consistency analysis of feature combinations

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study online classification of isolated handwritten symbols using distance measures on spaces of curves. We compare three distance-based measures on a vector space representation of curves to elastic matching and ensembles of SVM. We consider the Euclidean and Manhattan distances and the distance to the convex hull of nearest neighbors. We show experimentally that of all these methods the distance to the convex hull of nearest neighbors yields the best classification accuracy of about 97.5%. Any of the above distance measures can be used to find the nearest neighbors and prune totally irrelevant classes, but the Manhattan distance is preferable for this because it admits a very efficient implementation. We use the first few Legendre-Sobolev coefficients of the coordinate functions to represent the symbol curves in a finite-dimensional vector space and choose the optimal dimension and number of bits per coefficient by cross-validation. We discuss an implementation of the proposed classification scheme that will allow classification of a sample among hundreds of classes in a setting with strict time and storage limitations.