| Presentation | 2014-06-20 Real-time Sign Language Recognition based on three Elements of Sign Language Mika HATANO, Shinji SAKO, Tadashi KITAMURA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In sign language recognition, an unified recognizing method is necessary because of many methods to capture sign language motion by different sensor devices. We propose a method with abstraction of sign language motion based on three elements of sign language: hand's motion, position, and form. The method enables sign language recognition without depending on feature parameters. Furthermore, it also can handle large vocabulary recognition if we use large vocabulary dictionary to decide rules of abstraction. In this paper, we performed an experiment of sign language words recognition. In this experiment, we used HMM for recognition of moving, template matching of depth image for recognition of form, and the normal distribution learned by maximum likelihood estimation for recognition of position. Based on our proposal method, we prepared recognition models of each element and conducted an experiment of real-time 100 sign language words recognition based on a sign language words dictionary using the depth sensor, Kinect. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | sign language recognition / real-time / Kinect / HMM / template matching |
| Paper # | SP2014-58,WIT2014-13 |
| Date of Issue |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2014/6/12(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Well-being Information Technology(WIT) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Real-time Sign Language Recognition based on three Elements of Sign Language |
| Sub Title (in English) | |
| Keyword(1) | sign language recognition |
| Keyword(2) | real-time |
| Keyword(3) | Kinect |
| Keyword(4) | HMM |
| Keyword(5) | template matching |
| 1st Author's Name | Mika HATANO |
| 1st Author's Affiliation | Department of Computer Science and Engeneering, Graduaite School of Engeneering, Nagoya Institute of Technology() |
| 2nd Author's Name | Shinji SAKO |
| 2nd Author's Affiliation | Department of Computer Science and Engeneering, Graduaite School of Engeneering, Nagoya Institute of Technology |
| 3rd Author's Name | Tadashi KITAMURA |
| 3rd Author's Affiliation | Department of Computer Science and Engeneering, Graduaite School of Engeneering, Nagoya Institute of Technology |
| Date | 2014-06-20 |
| Paper # | SP2014-58,WIT2014-13 |
| Volume (vol) | vol.114 |
| Number (no) | 92 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |