Presentation | 1999/10/22 Artificial Neural Networks for Model Fitting in Machine Vision Atsushi IMIYA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The family of ascent equation χ=∇φ provides a framework for the minimization of the least-squares method. In machine vision φ=tr(XA) is a typical expression of the energy function. The minimum of this energy function determines the parameter of a model. Brockett introduces a dynamical system for a matching problem which is motivated by a basic problem in computer vision, matching for the motion analysis. His dynamics finds the matrix which minimizes φ. The present paper shows the relations among the principal component analysis and self-organization map as methods to solve the model fitting problem. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | The Hough Transform / Least-Squares Method / Model Fitting / Random Algorithms / Self-organization / Artificial Neural Networks |
Paper # | NC99-49 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1999/10/22(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 | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Artificial Neural Networks for Model Fitting in Machine Vision |
Sub Title (in English) | |
Keyword(1) | The Hough Transform |
Keyword(2) | Least-Squares Method |
Keyword(3) | Model Fitting |
Keyword(4) | Random Algorithms |
Keyword(5) | Self-organization |
Keyword(6) | Artificial Neural Networks |
1st Author's Name | Atsushi IMIYA |
1st Author's Affiliation | Department of Information and Image Sciences, Chiba University() |
Date | 1999/10/22 |
Paper # | NC99-49 |
Volume (vol) | vol.99 |
Number (no) | 383 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |