| Presentation | 2008-01-16 Gesture Recognition using Sparse Code of Hierarchical Self-Organizing Map Atsushi SHIMADA, Rin-ichiro TANIGUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose an approach to recognize time-series gesture patterns with Self-Organizing Map. The time length of a human gesture is not always same even if we compare the same gesture. Of course, when the gesture is different, the time length is obviously different. Therefore, the key issue of the time-series pattern recognition is to absorb the time variant appropriately and to make clusters which include the same gesture class. In our approach, we arrange the Self-Organizing Maps hierarchically. In each layer of the Self-Organizing Map, the time-series patterns divided into some periods rowdy. For example, postures which are the minimum unit of a gesture are learned in the first layer. In the second layer, short gestures which are consist of some time-series postures are learned. In this paper, we call such short gestures "gesture element". In the upper layer, gestures which are consist of some gesture elements are learned. In our approach, we use the activated pattern of neurons in the first layer, which we call "Sparse Code". The Self-Organizing Map can store the similar patterns on the neighbor neurons. This helps the Self-Organizing Map to create similar sparse code even if the time lengths of the gesture are different from each other in the same gesture class. Therefore, in the upper layer, the Self-Organizing Map can perform time invariant recognition of the gesture elements and gestures. In this paper, we explain how to learn and recognize the gesture patterns with the sparse codes of the hierarchical Self-Organizing Maps. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Hierarchical Self-Organizing Map / Gesture Recognition / Sparse Coding |
| Paper # | NC2007-104 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2008/1/8(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 | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Gesture Recognition using Sparse Code of Hierarchical Self-Organizing Map |
| Sub Title (in English) | |
| Keyword(1) | Hierarchical Self-Organizing Map |
| Keyword(2) | Gesture Recognition |
| Keyword(3) | Sparse Coding |
| 1st Author's Name | Atsushi SHIMADA |
| 1st Author's Affiliation | Department of Intelligent Systems, Kyushu University() |
| 2nd Author's Name | Rin-ichiro TANIGUCHI |
| 2nd Author's Affiliation | Department of Intelligent Systems, Kyushu University |
| Date | 2008-01-16 |
| Paper # | NC2007-104 |
| Volume (vol) | vol.107 |
| Number (no) | 413 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |