Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields

Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields

For centuries, in the North of Thailand, many books of Lanna Dharma characters had been printed. These books are the important sources of the knowledge of ancient Lanna wisdom. At present, the books are found old and damaged. Most of characters are rough and not clear according to its early printing...

Full description

Saved in:
Bibliographic Details
Main Authors: Chueaphun,C., Klomsae,A., Marukatat,S., Chaijaruwanich,J.
Format: Conference or Workshop Item
Published: 2015
Online Access:http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84881534939&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/38696
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-38696
record_format dspace
spelling th-cmuir.6653943832-386962015-06-16T07:53:58Z Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields Chueaphun,C. Klomsae,A. Marukatat,S. Chaijaruwanich,J. For centuries, in the North of Thailand, many books of Lanna Dharma characters had been printed. These books are the important sources of the knowledge of ancient Lanna wisdom. At present, the books are found old and damaged. Most of characters are rough and not clear according to its early printing technology at that time. Moreover, some sets of characters are relatively very similar which cause the difficulty to recognize them. This paper proposes a Lanna Dharma printed character recognition technique using k- Nearest Neighbor and Conditional Random Fields. The accuracy of recognition rate is about 82.61 percent. Copyright © 2012 SciTePress - Science and Technology Publications. 2015-06-16T07:53:58Z 2015-06-16T07:53:58Z 2012-12-01 Conference Paper 2-s2.0-84881534939 http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84881534939&origin=inward http://cmuir.cmu.ac.th/handle/6653943832/38696
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
description For centuries, in the North of Thailand, many books of Lanna Dharma characters had been printed. These books are the important sources of the knowledge of ancient Lanna wisdom. At present, the books are found old and damaged. Most of characters are rough and not clear according to its early printing technology at that time. Moreover, some sets of characters are relatively very similar which cause the difficulty to recognize them. This paper proposes a Lanna Dharma printed character recognition technique using k- Nearest Neighbor and Conditional Random Fields. The accuracy of recognition rate is about 82.61 percent. Copyright © 2012 SciTePress - Science and Technology Publications.
format Conference or Workshop Item
author Chueaphun,C.
Klomsae,A.
Marukatat,S.
Chaijaruwanich,J.
spellingShingle Chueaphun,C.
Klomsae,A.
Marukatat,S.
Chaijaruwanich,J.
Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
author_facet Chueaphun,C.
Klomsae,A.
Marukatat,S.
Chaijaruwanich,J.
author_sort Chueaphun,C.
title Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
title_short Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
title_full Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
title_fullStr Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
title_full_unstemmed Lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
title_sort lanna dharma printed character recognition using k-nearest neighbor and conditional random fields
publishDate 2015
url http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84881534939&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/38696
_version_ 1681421520385081344

Similar Items