The Impact of Large Training Sets on the Recognition Rate of Off-line Japanese Kanji Character Classifiers

Though it is commonly agreed that increasing the training set size leads to improved recognition rates, the deficit of publicly available Japanese character pattern databases prevents us from verifying this assumption empirically for large data sets. Whereas the typical number of training samples has usually been between 100-200 patterns per category until now, newly collected databases and increased computing power allows us to experiment with a much higher number of samples per category. In this paper, we experiment with off-line classifiers trained with up to 1550 patterns for 3036 categories respectively. We show that this bigger training set size indeed leads to improved recognition rates compared to the smaller training sets normally used.