Abstract

This paper describes a system for recognizing hand-printed digits using optimal bounded error matching. Bounded error matching is already in common use in general-purpose 2D and 3D visual object recognition and can cope with clutter, occlusions, and noise, important issues also in OCR. The results presented demonstrate that the same techniques achieve high recognition rates (up to 99.2\%) on a real-world hand- printed digit recognition task (the {NIST} database of hand-printed census forms and the {CEDAR} database of digits extracted from the {U.S.} mail ZIP codes). As part of the system, a post-processing step for k-nearest neighbor clasifiers based on decision trees is described that can be used (in place of the usual heuristic methods) for setting thresholds and that improves recognition rates significantly.

Details

Actions