TY - GEN
T1 - Accuracy improvement of handwritten numeral recognition by mirror image learning
AU - Wakabayashi, Tetsushi
AU - Shi, Meng
AU - Ohyama, Wataru
AU - Kimura, Fumitaka
N1 - Publisher Copyright:
© 2001 IEEE.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2001
Y1 - 2001
N2 - This paper proposes a new corrective learning algorithm and evaluates the performance by handwritten numeral recognition test. The algorithm generates a mirror image of a pattern that belongs to one class of a pair of confusing classes and utilizes it as a learning pattern of the other class. This paper also studies on how to extract confusing patterns within a certain margin of a decision boundary to generate enough number of mirror images, and how to perform an effective mirror image compensation to increase the margin. Recognition accuracies of the minimum distance classifier and the projection distance method were improved from 93.17% to 98.38% and from 99.11% to 99.41% respectively in the recognition test for handwritten numeral database IPTP CD-ROMI.
AB - This paper proposes a new corrective learning algorithm and evaluates the performance by handwritten numeral recognition test. The algorithm generates a mirror image of a pattern that belongs to one class of a pair of confusing classes and utilizes it as a learning pattern of the other class. This paper also studies on how to extract confusing patterns within a certain margin of a decision boundary to generate enough number of mirror images, and how to perform an effective mirror image compensation to increase the margin. Recognition accuracies of the minimum distance classifier and the projection distance method were improved from 93.17% to 98.38% and from 99.11% to 99.41% respectively in the recognition test for handwritten numeral database IPTP CD-ROMI.
UR - http://www.scopus.com/inward/record.url?scp=33749821737&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33749821737&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2001.953810
DO - 10.1109/ICDAR.2001.953810
M3 - Conference contribution
AN - SCOPUS:33749821737
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 338
EP - 343
BT - Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001
PB - IEEE Computer Society
T2 - 6th International Conference on Document Analysis and Recognition, ICDAR 2001
Y2 - 10 September 2001 through 13 September 2001
ER -