| Presentation | 2011-01-24 Dependence of input image on color image segmentation using Inhibitory Connected Pulse Coupled Neural Network Masahiro YOSHIHARA, Masato YONEKAWA, Hiroaki KUROKAWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The image segementation is effective technic to extract objects from an image. In conventional method, initialization that depends on the input image's feature is necessary to the image segmentation. Initialization as well as conventional method is unnecessary for image segmentation using Pulse Coupled Neural Network(PCNN). We had proposed the Inhibitory Connected PCNN(IC-PCNN) as the extended PCNN model for color image processing. Also, in our previous study, We showed that the optimization of inhibitory connections lead to the accarate color image segmentation using IC-PCNN. However, the optimization of inhibitory connections that depend on the image is required for color image segmentation using IC-PCNN due to optimum condition of inhibitory connections deffer with the input image's color. In this papar, we show the influence of the parameter on dependence of color image segmentation using IC-PCNN on the input image's feature. From the simulation results, we show that the parameter search valid to reduce dependence of color image segmentation using IC-PCNN on the input image. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | image segmentation / inhibitory connected pulse coupled neural network |
| Paper # | NLP2010-128,NC2010-92 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2011/1/17(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) | Dependence of input image on color image segmentation using Inhibitory Connected Pulse Coupled Neural Network |
| Sub Title (in English) | |
| Keyword(1) | image segmentation |
| Keyword(2) | inhibitory connected pulse coupled neural network |
| 1st Author's Name | Masahiro YOSHIHARA |
| 1st Author's Affiliation | School of Computer Science, Tokyo University of Technology() |
| 2nd Author's Name | Masato YONEKAWA |
| 2nd Author's Affiliation | School of Computer Science, Tokyo University of Technology |
| 3rd Author's Name | Hiroaki KUROKAWA |
| 3rd Author's Affiliation | School of Computer Science, Tokyo University of Technology |
| Date | 2011-01-24 |
| Paper # | NLP2010-128,NC2010-92 |
| Volume (vol) | vol.110 |
| Number (no) | 388 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |