2014 Fiscal Year Final Research Report
Study on facial expression recognition using thermal image processing and speech recognition in actual environment
| Project/Area Number |
22300077
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Kyoto Prefectural University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TABUSE Masayoshi 京都府立大学, 大学院生命環境科学研究科, 准教授 (10244188)
|
|---|
| Research Collaborator |
ASADA Taro 京都府立大学, 大学院生命環境科学研究科, 特任准教授
KATO Ryota 京都府立大学, 大学院生命環境科学研究科, 特任研究員
|
|---|
| Project Period (FY) |
2010-04-01 – 2015-03-31
|
| Keywords | 音声認識 / 表情認識 / 温度画像 / 正面判定 / 母音認識 / 表情強度 / テレビ電話 |
|---|
| Outline of Final Research Achievements |
We are missing the robot that can recognize facial expressions in taking care a person of advanced years and the robot that can talk with a person loving alone. The purpose of our study is to develop fundamental technologies which must be equipped with these robots for recognizing human state. It is assumed that the robot recognizes the facial expressions using thermal images at the following three timing-positions per utterance; just before speaking, in speaking the first and the last vowels. We have investigated the following issues in order; (1) facial expression recognition in speaking one word, (2) front-view judgment using thermal image, (3) parallel processing system, (4) performance of our system in actual environment, and (5) finding the next issues to be challenged. We have developed several methods and systems useful for designing the robot that can recognize facial expressions using the real-time processing in the natural conversation with human.
|
| Free Research Field |
感性情報学・ソフトコンピューティング
|
