TY - GEN
T1 - Multiresolution recognition of handwritten numerals with wavelet transform and multilayer cluster neural network
AU - Lee, Seong Whan
AU - Kim, Young Joon
N1 - Funding Information:
This research was supported by the Directed Basic Research Fund of Korea Science and Engineering Foundation.
Publisher Copyright:
© 1995 IEEE.
PY - 1995
Y1 - 1995
N2 - In this paper, we propose a new scheme for multiresolution recognition of totally unconstrained handwritten numerals using wavelet transform and a simple multilayer cluster neural network. The proposed scheme consists of two stages: A feature extraction stage for extracting multiresolution features with wavelet transform, and a classification stage for classifying totally unconstrained handwritten numerals with a simple multilayer cluster neural network. In order to verify the performance of the proposed scheme, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. The error rates were 3.20%, 0.83%, and 0.75%, respectively. These results showed that the proposed scheme is very robust in terms of various writing styles and sizes.
AB - In this paper, we propose a new scheme for multiresolution recognition of totally unconstrained handwritten numerals using wavelet transform and a simple multilayer cluster neural network. The proposed scheme consists of two stages: A feature extraction stage for extracting multiresolution features with wavelet transform, and a classification stage for classifying totally unconstrained handwritten numerals with a simple multilayer cluster neural network. In order to verify the performance of the proposed scheme, experiments with unconstrained handwritten numeral database of Concordia University of Canada, that of Electro-Technical Laboratory of Japan, and that of Electronics and Telecommunications Research Institute of Korea were performed. The error rates were 3.20%, 0.83%, and 0.75%, respectively. These results showed that the proposed scheme is very robust in terms of various writing styles and sizes.
UR - http://www.scopus.com/inward/record.url?scp=84961717868&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.1995.602073
DO - 10.1109/ICDAR.1995.602073
M3 - Conference contribution
AN - SCOPUS:84961717868
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 1010
EP - 1013
BT - Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995
PB - IEEE Computer Society
T2 - 3rd International Conference on Document Analysis and Recognition, ICDAR 1995
Y2 - 14 August 1995 through 16 August 1995
ER -