TY - GEN
T1 - Character image patterns as big data
AU - Uchida, Seiichi
AU - Ishida, Ryosuke
AU - Yoshida, Akira
AU - Cai, Wenjie
AU - Feng, Yaokai
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - The ambitious goal of this research is to understand the real distribution of character patterns. Ideally, if we can collect all possible character patterns, we can totally understand how they are distributed in the image space. In addition, we also have the perfect character recognizer because we know the correct class for any character image. Of course, it is practically impossible to collect all those patterns - however, if we collect character patterns massively and analyze how the distribution changes according to the increase of patterns, we will be able to estimate the real distribution asymptotically. For this purpose, we use 822,714 manually ground-truthed 32 × 32 handwritten digit patterns in this paper. The distribution of those patterns are observed by nearest neighbor analysis and network analysis, both of which do not make any approximation (such as low-dimensional representation) and thus do not corrupt the details of the distribution.
AB - The ambitious goal of this research is to understand the real distribution of character patterns. Ideally, if we can collect all possible character patterns, we can totally understand how they are distributed in the image space. In addition, we also have the perfect character recognizer because we know the correct class for any character image. Of course, it is practically impossible to collect all those patterns - however, if we collect character patterns massively and analyze how the distribution changes according to the increase of patterns, we will be able to estimate the real distribution asymptotically. For this purpose, we use 822,714 manually ground-truthed 32 × 32 handwritten digit patterns in this paper. The distribution of those patterns are observed by nearest neighbor analysis and network analysis, both of which do not make any approximation (such as low-dimensional representation) and thus do not corrupt the details of the distribution.
UR - http://www.scopus.com/inward/record.url?scp=84874256710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84874256710&partnerID=8YFLogxK
U2 - 10.1109/ICFHR.2012.190
DO - 10.1109/ICFHR.2012.190
M3 - Conference contribution
AN - SCOPUS:84874256710
SN - 9780769547749
T3 - Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR
SP - 479
EP - 484
BT - Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
T2 - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
Y2 - 18 September 2012 through 20 September 2012
ER -