Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/29346
Title: A general non-linear method for modelling shape and locating image objects
Authors: Lanitis, Andreas 
Sozou, Peter D. 
Taylor, Chris J. 
Cootes, Timothy F. 
Di Mauro, E. C. 
Major Field of Science: Engineering and Technology;Social Sciences
Field Category: Computer and Information Sciences;SOCIAL SCIENCES;Design
Keywords: Shape;Principal component analysis;Biomedical imaging;Deformable models;Multilayer perceptrons;Tellurium;Biophysics;Educational institutions;Ear;Face recognition
Issue Date: 25-Aug-1996
Source: Proceedings of 13th International Conference on Pattern Recognition, 1996, pp. 266-270
Start page: 266
End page: 270
Conference: 13th International Conference on Pattern Recognition 
Abstract: Objects of the same class often 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. Here we present a new form of PDM, which uses a multilayer perceptron (MLP) to carry out nonlinear principal component analysis. We demonstrate that MLP-PDMs can model the shape variability in classes of object for which the linear model fails. We describe the use of MLP-PDMs in image search and present quantitative results for a practical application (face recognition), demonstrating the ability to locate image structures accurately starting from a very poor initial approximation to their pose and shape. © 1996 IEEE.
URI: https://hdl.handle.net/20.500.14279/29346
DOI: 10.1109/ICPR.1996.547428
Rights: © Copyright IEEE
Type: Conference Papers
Affiliation : University College London 
The University of Manchester 
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

CORE Recommender
Show full item record

SCOPUSTM   
Citations 10

5
checked on Mar 14, 2024

Page view(s) 10

152
Last Week
0
Last month
6
checked on Nov 12, 2024

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons