Character image patterns as big data

Seiichi Uchida, Ryosuke Ishida, Akira Yoshida, Wenjie Cai, Yaokai Feng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
Pages479-484
Number of pages6
DOIs
Publication statusPublished - Dec 1 2012
Event13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 - Bari, Italy
Duration: Sep 18 2012Sep 20 2012

Publication series

NameProceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR
ISSN (Print)1550-5235

Other

Other13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
CountryItaly
CityBari
Period9/18/129/20/12

Fingerprint

Electric network analysis
Big data

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Uchida, S., Ishida, R., Yoshida, A., Cai, W., & Feng, Y. (2012). Character image patterns as big data. In Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 (pp. 479-484). [6424441] (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR). https://doi.org/10.1109/ICFHR.2012.190

Character image patterns as big data. / Uchida, Seiichi; Ishida, Ryosuke; Yoshida, Akira; Cai, Wenjie; Feng, Yaokai.

Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. p. 479-484 6424441 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Uchida, S, Ishida, R, Yoshida, A, Cai, W & Feng, Y 2012, Character image patterns as big data. in Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012., 6424441, Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR, pp. 479-484, 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012, Bari, Italy, 9/18/12. https://doi.org/10.1109/ICFHR.2012.190
Uchida S, Ishida R, Yoshida A, Cai W, Feng Y. Character image patterns as big data. In Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. p. 479-484. 6424441. (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR). https://doi.org/10.1109/ICFHR.2012.190
Uchida, Seiichi ; Ishida, Ryosuke ; Yoshida, Akira ; Cai, Wenjie ; Feng, Yaokai. / Character image patterns as big data. Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. pp. 479-484 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR).
@inproceedings{2bc74719305e4de596861e7eb49d9513,
title = "Character image patterns as big data",
abstract = "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.",
author = "Seiichi Uchida and Ryosuke Ishida and Akira Yoshida and Wenjie Cai and Yaokai Feng",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICFHR.2012.190",
language = "English",
isbn = "9780769547749",
series = "Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR",
pages = "479--484",
booktitle = "Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012",

}

TY - GEN

T1 - Character image patterns as big data

AU - Uchida, Seiichi

AU - Ishida, Ryosuke

AU - Yoshida, Akira

AU - Cai, Wenjie

AU - Feng, Yaokai

PY - 2012/12/1

Y1 - 2012/12/1

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

ER -