Analysis of Features for Efficient Japanese Vowel Recognition(Pattern Recognition)
スポンサーリンク
概要
- 論文の詳細を見る
This paper analyses the features required to efficiently recognize five Japanese vowels for lip-reading. Various features, such as shape and radius, are calculated from the lip region and fed to the k Nearest Neighbor method. We calculated 15 feature sets and found that the feature set including the area and aspect ratio of the mouth cavity is effective for Japanese vowel recognition.
- 社団法人電子情報通信学会の論文
- 2007-11-01
著者
-
KONISHI Ryosuke
Faculty of Engineering, Tottori University
-
Saitoh Takeshi
Tottori Univ. Tottori‐shi Jpn
-
SAITOH Takeshi
Faculty of Engineering, Tottori Univesity
-
HISAGI Mitsugu
Faculty of Engineering, Tottori Univesity
-
Hisagi Mitsugu
Faculty Of Engineering Tottori Univesity
-
Konishi Ryosuke
Tottori Univ. Tottori Jpn
関連論文
- Microscopic Analysis of the Degradation Mechanism of Gallium Arsenide Metal-Semiconductor Field-Effect Transistor
- Light Emission and Surface States Annealing on GaAs Metal Semiconductor Field-Effect Transistor
- Decrease in Surface States on GaAs Metal-Semiconductor Field-Effect Transistor by High Temperature Operation
- Analysis of Surface States of Gallium Arsenide Metal Semiconductor Field-Effect Transistors using Drain Current Transients under Light Illumination
- Analysis of Gate Lag in GaAs Metal-Semiconductor Field-Effect Transistor Using Light Illumination
- Study on the development of a practical system for discrimination and concentration-estimation of domestic gases
- The Periodic Operation of a Semiconductor Gas Sensor and Its Application to the Discrimination of Inflammable Gases
- Analysis of Features for Efficient Japanese Vowel Recognition(Pattern Recognition)
- Analysis of Surface States of Gallium Arsenide Metal Semiconductor Field-Effect Transistors using Drain Current Transients under Light Illumination