The effect of large training set sizes on online Japanese Kanji and English cursive recognizers

H.A. Rowley1, M. Goyal1, J. Bennett1
1Microsoft Corporation, Redmond, WA, USA

Tóm tắt

Much research in handwriting recognition has focused on how to improve recognizers with constrained training set sizes. This paper presents the results of training a nearest-neighbor based online Japanese Kanji recognizer and a neural-network based online cursive English recognizer on a wide range of training set sizes, including sizes not generally available. The experiments demonstrate that increasing the amount of training data improves the accuracy, even when the recognizer's representation power is limited.

Từ khóa

#Handwriting recognition #Character recognition #Prototypes #Training data #Writing #Neural networks #Ink #Sparse matrices #Frequency #Delay effects

Tài liệu tham khảo

dai, 1998, Handwritten symbol recognizer, US Patent, 5, 729 10.1142/9789814503549_0009 adcock, 1998, Method and system for modeling handwriting using polynomials as a function of time, US Patent, 5, 764 rumelhart, 1992, Theory to practice: A case study-recognizing cursive handwriting, Computational Learning and Cognition Proceedings of the Third NEC Research Symposium Copyright, 177 hullender, 2000, Automatic generation of handwriting recognition crossing tables, US Patent, 6, 94 10.1007/BF00336740 guha, 1998, A uniform compact representation for variable size ink, US patent pending