Dr. Takeshi Saitoh Profile

Dr. Takeshi Saitoh

at Kyushu Institute of Technology

SPIE Involvement:

Author

Publications (7)

Proceedings Article | 25 March 2024 Paper

Construction of a new database for Japanese lip-reading

Towa Yamabe, Takeshi Saitoh

Proceedings Volume 13089, 1308911 (2024) https://doi.org/10.1117/12.3021119

Read Abstract +

Proceedings Article | 25 March 2024 Paper

KuchiNavi: lip-reading-based navigation app

Tatsuya Kanamaru, Takeshi Saitoh

Proceedings Volume 13089, 130891C (2024) https://doi.org/10.1117/12.3021118

Read Abstract +

Proceedings Article | 16 February 2022 Paper

3DCNN-based mouth shape recognition for patient with intractable neurological diseases

Yuya Nakamura, Takeshi Saitoh, Kazuyuki Itoh

Proceedings Volume 12083, 120832H (2022) https://doi.org/10.1117/12.2623642

KEYWORDS: Mouth, Telecommunications, Optical flow, Visualization, Speech recognition, Facial recognition systems

Read Abstract +

Proceedings Article | 16 February 2022 Paper

Replacing speaker-independent recognition task with speaker-dependent task for lip-reading using First Order Motion Model

Michinari Kodama, Takeshi Saitoh

Proceedings Volume 12083, 1208323 (2022) https://doi.org/10.1117/12.2623640

KEYWORDS: Databases, Motion models, Speaker recognition, Image processing, Feature extraction, Video, Skin, Mouth, Cameras, Speech recognition

Read Abstract +

Proceedings Article | 3 January 2020 Paper

Automatic tree species identification from natural bark image

Junya Ido, Takeshi Saitoh

Proceedings Volume 11373, 1137305 (2020) https://doi.org/10.1117/12.2557187

KEYWORDS: Image segmentation, Image processing, Target recognition, Convolutional neural networks

Read Abstract +

Proceedings Article | 6 May 2019 Paper

CNN-based tree species identification from bark image

Junya Ido, Takeshi Saitoh

Proceedings Volume 11069, 110693G (2019) https://doi.org/10.1117/12.2524213

KEYWORDS: Convolutional neural networks, Image processing, Object recognition

Read Abstract +

Proceedings Article | 6 May 2019 Paper

Character input system based on gaze input using wearable camera

Warapon Chinsatit, Nagisa Kondo, Takeshi Saitoh

Proceedings Volume 11069, 1106930 (2019) https://doi.org/10.1117/12.2524411

KEYWORDS: Cameras, Eye, Image processing, Data modeling, Optical character recognition, Infrared cameras, Convolutional neural networks

Read Abstract +

Showing 5 of 7 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years