Classification of characters by man and by machine

摘要

In this paper the performance of a nearly optimal system for character recognition is compared to human performance on the same data set. The recognition system uses a linear feature extraction method which is superior to discrete Karhunen-Loeve expansion. The experiments consider binary and multiple classification of handprinted characters, binary classification of similar characters of one font corrupted by additive white normal noise, and multiple classification of truncated handprinted characters. It turns out that the human visual system is superior in recognizing handprinted characters and inferior in the case of single font characters with additive noise.