講演抄録/キーワード |
講演名 |
2011-03-10 11:40
Online Handwritten character recognition by MRF for Lao characters ○Latsamy Saysourinhong・Bilan Zhu・Masaki Nakagawa(Tokyo Univ. of Agric. and Tech.) PRMU2010-245 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
This paper describes on-line recognition of handwritten Lao characters which include consonants, vowels and tone marks, 52 characters in total by adopting Markov random field (MRF). It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method |
キーワード |
(和) |
/ / / / / / / |
(英) |
Online handwritten character recognition / Lao character recognition / Markov random field / / / / / |
文献情報 |
信学技報, vol. 110, no. 467, PRMU2010-245, pp. 49-54, 2011年3月. |
資料番号 |
PRMU2010-245 |
発行日 |
2011-03-03 (PRMU) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2010-245 |