| Presentation | 2016-10-16 Sign language recognition by convolutional neural network with concatenated sequence image of depth image Keisuke Hashimura, Takeshi Saitoh, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We proposed a concatenated frame image (CFI) that some sampled frame images from the scene are concatenated like a two-dimensional tile, and proposed a framework of CFI-based convolutional neural network (CNN). In this paper, we propose an improved CFI for sign language scene and CFI-based CNN for sign language recognition (SLR). The proposed method was evaluated with 100 words of sign language acquired by Kinect sensor. As the result, right-hand based CFI obtained the highest recognition accuracy. This performance is better than the traditional method which involved not only the hand shape but also hand location and its movement. It is confirmed that the proposed method is efficient for SLR. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sign language recognition / depth image / convolutional neural network / concatenated sequence image |
| Paper # | WIT2016-36 |
| Date of Issue | 2016-10-09 (WIT) |
| Conference Information | |
| Committee | WIT |
|---|---|
| Conference Date | 2016/10/16(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Karatsu Royal Hotel (Saga pref.) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Ergonomics and Well-being Information Technology, etc. |
| Chair | Kiyohiko Nunokawa(Tokyo International Univ.) |
| Vice Chair | Chikamune Wada(Kyushu Inst. of Tech.) |
| Secretary | Chikamune Wada(Nagoya Inst. of Tech.) |
| Assistant | Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) / Takashi Handa(Saitama Industrial Technology Center) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Sign language recognition by convolutional neural network with concatenated sequence image of depth image |
| Sub Title (in English) | |
| Keyword(1) | Sign language recognition |
| Keyword(2) | depth image |
| Keyword(3) | convolutional neural network |
| Keyword(4) | concatenated sequence image |
| 1st Author's Name | Keisuke Hashimura |
| 1st Author's Affiliation | Kyushu Institute of Technology(kyutech) |
| 2nd Author's Name | Takeshi Saitoh |
| 2nd Author's Affiliation | Kyushu Institute of Technology(kyutech) |
| Date | 2016-10-16 |
| Paper # | WIT2016-36 |
| Volume (vol) | vol.116 |
| Number (no) | WIT-248 |
| Page | pp.pp.17-22(WIT), |
| #Pages | 6 |
| Date of Issue | 2016-10-09 (WIT) |