Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/1952
Title: | Non-linear point distribution modelling using a multi-layer perceptron |
Authors: | Sozou, Peter D. Cootes, Timothy F. Taylor, Chris J. Di Mauro, E. C. Lanitis, Andreas |
metadata.dc.contributor.other: | Λανίτης, Ανδρέας |
Major Field of Science: | Social Sciences |
Keywords: | Point distribution modelling;Multi-layer perceptron;Shape variation |
Issue Date: | Jun-1997 |
Source: | Image and Vision Computing,1997, vol. 15, no. 6, pp. 457-463 |
Volume: | 15 |
Issue: | 6 |
Start page: | 457 |
End page: | 463 |
Journal: | Image and Vision Computing |
Abstract: | Objects of the same class sometimes exhibit variation in shape. This shape variation has previously been modelled by means of point distribution models (PDMs) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. A polynomial regression generalization of PDMs, which succeeds in capturing certain forms of non-linear shape variability, has also been described. Here we present a new form of PDM, which uses a multi-layer perceptron to carry out non-linear principal component analysis. We compare the performance of the new model with that of the existing models on two classes of variable shape: one exhibits bending, and the other exhibits complete rotation. The linear PDM fails on both classes of shape; the polynomial regression model succeeds for the first class of shapes but fails for the second; the new multi-layer perceptron model performs well for both classes of shape. The new model is the most general formulation for PDMs which has been proposed to date. |
URI: | https://hdl.handle.net/20.500.14279/1952 |
ISSN: | 02628856 |
DOI: | 10.1016/S0262-8856(96)00001-7 |
Rights: | © Elsevier |
Type: | Article |
Affiliation : | University College London The University of Manchester Cyprus College |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
Sorry the service is unavailable at the moment. Please try again later.
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.