Presentation 2016-09-05
Stroke-by-stroke Order Evaluation of Online Handwritten Kanji Characters using Directional Feature
Kazuhiro Mita, Masaki Nakagawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a stroke order evaluation method for online handwritten Kanji characters written on a tablet. Previously, we presented a method employing shape context feature around each feature point. In this paper, we propose a method that extracts directional features around a focused feature point in square areas divided by horizontal and vertical grids. As often employed for character recognition, the method divides a handwritten Kanji pattern into 8 * 8 squares and extracts 8 directional features from each square. An experiment using 1,005 kinds of Kanji characters shows that the proposed method evaluates stroke order correctly by 97.5% with the maximum time of 0.05 sec. /character. This accuracy is less than 98.4% of the previous method by 0.9 points, but its speed is more than two times improved from 0.12 sec. We also made another experiment for 26 kinds of Kanji characters which are often written in wrong stroke order. The experiment shows that the proposed method evaluates stroke order correctly by 97.9% with the maximum time of 0.01 sec. /character. This accuracy is less than 98.6% of the previous method by 0.7 points, but its speed is more than three times improved from 0.03 sec.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Computer Assisted Learning / Stroke Order Evaluation / Directional Feature / On-line handwritten character recognition
Paper # PRMU2016-54,IBISML2016-9
Date of Issue 2016-08-29 (PRMU, IBISML)

Conference Information
Committee PRMU / IPSJ-CVIM / IBISML
Conference Date 2016/9/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Eisaku Maeda(NTT) / / Kenji Fukumizu(ISM)
Vice Chair Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.)
Secretary Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Nagoya Inst. of Tech.)
Assistant Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / / Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stroke-by-stroke Order Evaluation of Online Handwritten Kanji Characters using Directional Feature
Sub Title (in English)
Keyword(1) Computer Assisted Learning
Keyword(2) Stroke Order Evaluation
Keyword(3) Directional Feature
Keyword(4) On-line handwritten character recognition
1st Author's Name Kazuhiro Mita
1st Author's Affiliation Tokyo University of Agriculture and Technology(Tokyo Univ. of Agri. & Tech.)
2nd Author's Name Masaki Nakagawa
2nd Author's Affiliation Tokyo University of Agriculture and Technology(Tokyo Univ. of Agri. & Tech.)
Date 2016-09-05
Paper # PRMU2016-54,IBISML2016-9
Volume (vol) vol.116
Number (no) PRMU-208,IBISML-209
Page pp.pp.1-5(PRMU), pp.1-5(IBISML),
#Pages 5
Date of Issue 2016-08-29 (PRMU, IBISML)