| Presentation | 2017-01-19 ngle independent lip reading using symmetrical 3D-AAM of facial images Takuya Watanabe, Kouichi Katsurada, Yasushi Kanazawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Lip reading is a technique to recognize spoken words from only visual images of a face. There have been proposed various approaches for lip reading, most of them, however, do not achieve enough performance for non-frontal images because of self-occlusion. In this paper, we propose an angle-independent lip-reading system that prevents deterioration of performance caused by self-occlusion using a symmetric facial model with 3D-AAM. We adopt HMM for modeling the variety of mouth shapes and use it for lip reading. The experimental results show that the recognition accuracy using symmetrical 3D-AAM increases by more than 4% compared with normal 3D-AAM when the view angle is 90 degree. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Lip reading / Symmetry model / 3D-AAM / View Independency |
| Paper # | PRMU2016-134,MVE2016-25 |
| Date of Issue | 2017-01-12 (PRMU, MVE) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM / MVE |
|---|---|
| Conference Date | 2017/1/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / / Yoshinari Kameda(Univ. of Tsukuba) |
| Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / / Kenji Mase(Nagoya Univ.) |
| Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / / Kenji Mase(Kyushu Univ.) |
| Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / / Hideaki Uchiyama(Kyushu Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(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 Multimedia and Virtual Environment |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | ngle independent lip reading using symmetrical 3D-AAM of facial images |
| Sub Title (in English) | |
| Keyword(1) | Lip reading |
| Keyword(2) | Symmetry model |
| Keyword(3) | 3D-AAM |
| Keyword(4) | View Independency |
| 1st Author's Name | Takuya Watanabe |
| 1st Author's Affiliation | Toyohashi University of Technology(TUT) |
| 2nd Author's Name | Kouichi Katsurada |
| 2nd Author's Affiliation | Tokyo University of Science(TUS) |
| 3rd Author's Name | Yasushi Kanazawa |
| 3rd Author's Affiliation | Toyohashi University of Technology(TUT) |
| Date | 2017-01-19 |
| Paper # | PRMU2016-134,MVE2016-25 |
| Volume (vol) | vol.116 |
| Number (no) | PRMU-411,MVE-412 |
| Page | pp.pp.135-140(PRMU), pp.135-140(MVE), |
| #Pages | 6 |
| Date of Issue | 2017-01-12 (PRMU, MVE) |