A high-accuracy syntactic recognition algorithm for handwritten numerals

1 January 1985

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics

Vol. SMC-15 (1) , 152-158
https://doi.org/10.1109/TSMC.1985.6313404

Abstract

A new set of topological features (primitives) for use with a syntactic classifier for high-accuracy recognition of handwritten numerals is proposed. The tree grammar used in this study makes it possible to achieve high-recognition speeds with minimal preprocessing of the test pattern.

Keywords

IMAGE EDGE DETECTION
SYNTACTICS
HANDWRITING RECOGNITION
CYBERNETICS
ACCURACY
EDUCATIONAL INSTITUTIONS