Recognition of Handprinted Digits1
using Optimal Bounded Error Matching
Thomas M. Breuel
IDIAP, C.P. 609, 1920 Martigny, Switzerland
This paper describes a system that recognizes hand-printed digits. The system is based on optimal bounded error matching, a technique already in common use in general-purpose 2D and 3D visual object recognition systems in cluttered, noisy scenes. In this paper, we demonstrate that the same techniques achieve high recognition rates (up to 99.2%) on real-world data (the NIST database of hand-printed census forms and the CEDAR database of digits extracted from U.S. mail ZIP codes).
As part of the system, we describe a post-processing step for k-nearest neighbor classifiers based on decision trees that can be used (in place of the usual heuristic methods) for setting thresholds and improves recognition rates significantly.
Keywords: ZIP codes, digit boundary, unconstrained handwritten digit recognition, presegmented handwritten digit recognition, nearest neighbor classification, decision trees, classification trees.
1A version of this paper has appeared in ICDAR '93 (Breuel, 1993).