| Presentation | 2002/3/11 Real Time Recognition of Shape and Position of Human Face by Two-D Spreading Associative Neural Network Yoshihiro TAHATA, Hirokazu KANAYAMA, Kiyomi NAKAMURA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The "Spreading associative neural network"(SAN-net), which is constructed based on the spatial recognition system in the brain, not only recognizes the shape of an object irrespective of its position, but also recognizes its position irrespective of its shape in the input pattern. The original SAN-net performed the recognition by off-line processing using still picture files. We extended the original system to the real-time recognition system which performed the recognition by on-line processing using serial uptake image from a video camera. We investigated and evaluated the recognition characteristics of the real-time recognition system. In the recognition experiment of front faces, the system recognized with sufficient accuracy both shape and position. Regarding the generalization ability, the real-time recognition system recognized 0.8 1.2 times in the scale changes, and up to ± 4 5°degrees in view plane rotation of the faces. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Position Invariant Shape Recognition / Shape Invariant Position Recognition / Real-Time Recognition / Face |
| Paper # | NC2001-141 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2002/3/11(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) | Real Time Recognition of Shape and Position of Human Face by Two-D Spreading Associative Neural Network |
| Sub Title (in English) | |
| Keyword(1) | Position Invariant Shape Recognition |
| Keyword(2) | Shape Invariant Position Recognition |
| Keyword(3) | Real-Time Recognition |
| Keyword(4) | Face |
| 1st Author's Name | Yoshihiro TAHATA |
| 1st Author's Affiliation | Graduate School of Engineering Toyama Prefectural University() |
| 2nd Author's Name | Hirokazu KANAYAMA |
| 2nd Author's Affiliation | Graduate School of Engineering Toyama Prefectural University |
| 3rd Author's Name | Kiyomi NAKAMURA |
| 3rd Author's Affiliation | Graduate School of Engineering Toyama Prefectural University |
| Date | 2002/3/11 |
| Paper # | NC2001-141 |
| Volume (vol) | vol.101 |
| Number (no) | 735 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |