Machine recognition of handwritten words: A project report

Abstract A project beginning with publication of the author's book Recognition in 1965 has resulted in a cursive script recognition program which has correctly identified 79 per cent of a test sample of 84 words. This program makes no use of information about sequence of stroke inscription, and segments the cursive line as part of the recognition procedure. It thus compares favorably in performance level with previously reported programs appropriately “normalized”, while not requiring input pertaining to stroke sequence and stroke segmentation that is essential to these other programs.