Presentation | 2001/2/2 Fast and accurate edge extraction by shape representation neural network with initial parameters by Hough transform Akio Furuhata, Itsuo Kumazawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, we present a coding method for edges using the multi-layer neural network in which neurons representing basic boundarys(ellipse and line)are combined to represent complex boundaries. The parameters of these basic boundaries are computed quickly and accurately by applying back propagation learning to initial values obtained by Hough transform. The rough parameters obtained by Hough transform are adjusted by learning argorithm of neural network. By conducting basic experiments, we verify the effectiveness of the system. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Image Coding / Shape discription / Hough transform |
Paper # | NC2000-97 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2001/2/2(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) | Fast and accurate edge extraction by shape representation neural network with initial parameters by Hough transform |
Sub Title (in English) | |
Keyword(1) | Image Coding |
Keyword(2) | Shape discription |
Keyword(3) | Hough transform |
1st Author's Name | Akio Furuhata |
1st Author's Affiliation | Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology() |
2nd Author's Name | Itsuo Kumazawa |
2nd Author's Affiliation | Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology |
Date | 2001/2/2 |
Paper # | NC2000-97 |
Volume (vol) | vol.100 |
Number (no) | 618 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |