Presentation 2015-05-15
Segmentation and Classification of the Added Marks for Writer Adaptable Handwritten Hiragana Character Recognition
Isamu Fujii, Hiroharu Kawanaka, Haruhiko Takase, Hisanori Yagami, Shinji Tsuruoka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Handwritten recognition system is used widely for the image captured by a digital camera, an image scanner or a touch panel. In previous research, we had proposed a Japanese character recognition method using the character set of a similar writer in order to reduce the burden on the user and to improve the recognition accuracy of the characters. We obtained the higher recognition accuracy of personal character recognition (94.3%) than the general dictionary that is generated by many writers. The accuracy rate 94.3% was the mean of the all categories, and the accuracy rate of the character with added marks, which are “Dakuten ( ゛)” mark and “Han-dakuten( ゜) ” mark, was 86.8%. The reason of the lower accuracy rate is that the locations of added marks have a large variation. In this paper, we propose a new approach for the character with the added marks recognition, which divides the form of a candidate character into a base character and an added character. We construct the algorithm of segmentation on “added marks” and classification of two “added marks” that is, “Dakuten” and “Han-dakuten”. We obtained 95.3% correct classification rate.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) handwritten character recognition / similar writer / Japanese Hiragana / added mark / classification
Paper # SIP2015-31,IE2015-31,PRMU2015-31,MI2015-31
Date of Issue 2015-05-07 (SIP, IE, PRMU, MI)

Conference Information
Committee PRMU / MI / IE / SIP
Conference Date 2015/5/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kazuhiko Sumi(Aoyama Gakuin Univ.) / Akinobu Shimizu(Tokyo Univ. of Agric. and Tech.) / Toshiaki Fujii(Nagoya Univ.) / Yoshinobu Kajikawa(Kansai Univ.)
Vice Chair Koichi Kise(Osaka Pref. Univ.) / Shuji Senda(NEC) / Yoshitaka Masutani(Hiroshima City Univ.) / Kensaku Mori(Nagoya Univ.) / Seishi Takamura(NTT) / Takayuki Hamamoto(Tokyo Univ. of Science) / Osamu Houshuyama(NEC) / Makoto Nakashizuka(Chiba Inst. of Tech.)
Secretary Koichi Kise(Kyushu Univ.) / Shuji Senda(Omron) / Yoshitaka Masutani(Tokushima Univ.) / Kensaku Mori(Kinki Univ.) / Seishi Takamura(NHK) / Takayuki Hamamoto(KDDI R&D Labs.) / Osamu Houshuyama(Ritsumeikan Univ.) / Makoto Nakashizuka(NEC)
Assistant Wataru Ohyama(Mie Univ.) / Mitsuru Anbai(DENSO IT Lab.) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidetaka Hontani(Nagoya Inst. of Tech.) / Shohei Matsuo(NTT) / Takamichi Miyata(Chiba Inst. of Tech.) / Takamichi Miyata(Chiba Inst. of Tech.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Medical Imaging / Technical Committee on Image Engineering / Technical Committee on Signal Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Segmentation and Classification of the Added Marks for Writer Adaptable Handwritten Hiragana Character Recognition
Sub Title (in English)
Keyword(1) handwritten character recognition
Keyword(2) similar writer
Keyword(3) Japanese Hiragana
Keyword(4) added mark
Keyword(5) classification
1st Author's Name Isamu Fujii
1st Author's Affiliation Mie University(Mie Univ.)
2nd Author's Name Hiroharu Kawanaka
2nd Author's Affiliation Mie University(Mie Univ.)
3rd Author's Name Haruhiko Takase
3rd Author's Affiliation Mie University(Mie Univ.)
4th Author's Name Hisanori Yagami
4th Author's Affiliation Mie University(Mie Univ.)
5th Author's Name Shinji Tsuruoka
5th Author's Affiliation Mie University(Mie Univ.)
Date 2015-05-15
Paper # SIP2015-31,IE2015-31,PRMU2015-31,MI2015-31
Volume (vol) vol.115
Number (no) SIP-22,IE-23,PRMU-24,MI-25
Page pp.pp.167-171(SIP), pp.167-171(IE), pp.167-171(PRMU), pp.167-171(MI),
#Pages 5
Date of Issue 2015-05-07 (SIP, IE, PRMU, MI)