Presentation 2017-06-01
A method of lip recognition using a convolutional neural network
Kazuya Okano, Hideaki orii, Hideaki kawano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, lip reading has been used in various fields such as communication with deaf person, understanding the content of utterance in scenes where speech is difficult to hear, and assistance for speech training. Lip reading is closely related to lip shape. Therefore, it is important to recognize lip shape. Many researchers are conducting various studies to recognize the lip shape. But most studies can distinguish only the outer contour of lip shape. It is important to identify the inner contour of lip shape when people read lip. In this article, we propose a method to distinguish outer contour and inner contour of lip shape simultaneously.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Lip recognition / Convolutional neural network / inner contour / outer contour
Paper # SIS2017-10
Date of Issue 2017-05-25 (SIS)

Conference Information
Committee SIS
Conference Date 2017/6/1(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Housen-Sou (Beppu)
Topics (in Japanese) (See Japanese page)
Topics (in English) Smart Personal Systems, etc.
Chair Hirokazu Tanaka(Hiroshima City Univ.)
Vice Chair Takayuki Nakachi(NTT) / Noriaki Suetake(Yamaguchi Univ.)
Secretary Takayuki Nakachi(Kanagawa Inst. of Tech.) / Noriaki Suetake(Kyushu Inst. of Tech.)
Assistant Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Takanori Koga(TCT)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A method of lip recognition using a convolutional neural network
Sub Title (in English)
Keyword(1) Lip recognition
Keyword(2) Convolutional neural network
Keyword(3) inner contour
Keyword(4) outer contour
1st Author's Name Kazuya Okano
1st Author's Affiliation Kyushu Institute of Technology(Kyutech)
2nd Author's Name Hideaki orii
2nd Author's Affiliation Fukuoka University(Fukuoka Univ)
3rd Author's Name Hideaki kawano
3rd Author's Affiliation Kyushu Institute of Technology(Kyutech)
Date 2017-06-01
Paper # SIS2017-10
Volume (vol) vol.117
Number (no) SIS-70
Page pp.pp.51-54(SIS),
#Pages 4
Date of Issue 2017-05-25 (SIS)