Analysis of local features for handwritten character recognition

Seiichi Uchida, Marcus Liwicki

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

4 Citations (Scopus)

Abstract

This paper investigates a part-based recognition method of handwritten digits. In the proposed method, the global structure of digit patterns is discarded by representing each pattern by just a set of local feature vectors. The method is then comprised of two steps. First, each of J local feature vectors of a target pattern is recognized into one of ten categories ("0"-"9") by the nearest neighbor discrimination with a large database of reference vectors. Second, the category of the target pattern is determined by the majority voting on the J local recognition results. Despite a pessimistic expectation, we have reached recognition rates much higher than 90% for the task of digit recognition.

Original languageEnglish
Title of host publicationProceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Pages1945-1948
Number of pages4
DOIs
Publication statusPublished - Nov 18 2010
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: Aug 23 2010Aug 26 2010

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CountryTurkey
CityIstanbul
Period8/23/108/26/10

Fingerprint

Character recognition

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Uchida, S., & Liwicki, M. (2010). Analysis of local features for handwritten character recognition. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010 (pp. 1945-1948). [5597243] (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2010.479

Analysis of local features for handwritten character recognition. / Uchida, Seiichi; Liwicki, Marcus.

Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 1945-1948 5597243 (Proceedings - International Conference on Pattern Recognition).

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

Uchida, S & Liwicki, M 2010, Analysis of local features for handwritten character recognition. in Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010., 5597243, Proceedings - International Conference on Pattern Recognition, pp. 1945-1948, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 8/23/10. https://doi.org/10.1109/ICPR.2010.479
Uchida S, Liwicki M. Analysis of local features for handwritten character recognition. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 1945-1948. 5597243. (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2010.479
Uchida, Seiichi ; Liwicki, Marcus. / Analysis of local features for handwritten character recognition. Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. pp. 1945-1948 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{b89aafc12c624f39880ddc35976913b9,
title = "Analysis of local features for handwritten character recognition",
abstract = "This paper investigates a part-based recognition method of handwritten digits. In the proposed method, the global structure of digit patterns is discarded by representing each pattern by just a set of local feature vectors. The method is then comprised of two steps. First, each of J local feature vectors of a target pattern is recognized into one of ten categories ({"}0{"}-{"}9{"}) by the nearest neighbor discrimination with a large database of reference vectors. Second, the category of the target pattern is determined by the majority voting on the J local recognition results. Despite a pessimistic expectation, we have reached recognition rates much higher than 90{\%} for the task of digit recognition.",
author = "Seiichi Uchida and Marcus Liwicki",
year = "2010",
month = "11",
day = "18",
doi = "10.1109/ICPR.2010.479",
language = "English",
isbn = "9780769541099",
series = "Proceedings - International Conference on Pattern Recognition",
pages = "1945--1948",
booktitle = "Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010",

}

TY - GEN

T1 - Analysis of local features for handwritten character recognition

AU - Uchida, Seiichi

AU - Liwicki, Marcus

PY - 2010/11/18

Y1 - 2010/11/18

N2 - This paper investigates a part-based recognition method of handwritten digits. In the proposed method, the global structure of digit patterns is discarded by representing each pattern by just a set of local feature vectors. The method is then comprised of two steps. First, each of J local feature vectors of a target pattern is recognized into one of ten categories ("0"-"9") by the nearest neighbor discrimination with a large database of reference vectors. Second, the category of the target pattern is determined by the majority voting on the J local recognition results. Despite a pessimistic expectation, we have reached recognition rates much higher than 90% for the task of digit recognition.

AB - This paper investigates a part-based recognition method of handwritten digits. In the proposed method, the global structure of digit patterns is discarded by representing each pattern by just a set of local feature vectors. The method is then comprised of two steps. First, each of J local feature vectors of a target pattern is recognized into one of ten categories ("0"-"9") by the nearest neighbor discrimination with a large database of reference vectors. Second, the category of the target pattern is determined by the majority voting on the J local recognition results. Despite a pessimistic expectation, we have reached recognition rates much higher than 90% for the task of digit recognition.

UR - http://www.scopus.com/inward/record.url?scp=78149491437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149491437&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.479

DO - 10.1109/ICPR.2010.479

M3 - Conference contribution

AN - SCOPUS:78149491437

SN - 9780769541099

T3 - Proceedings - International Conference on Pattern Recognition

SP - 1945

EP - 1948

BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010

ER -