A study on the application of eigenvectors to the recognition of line-drawn faces

Pao Yue-kong Library Electronic Theses Database

A study on the application of eigenvectors to the recognition of line-drawn faces


Author: Chia, Stephen Si-wai
Title: A study on the application of eigenvectors to the recognition of line-drawn faces
Degree: M.Sc.
Year: 1998
Subject: Face perception -- Computer simulation
Optical pattern recognition
Principal components analysis
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Pages: viii, 133 leaves : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1421113
URI: http://theses.lib.polyu.edu.hk/handle/200/1306
Abstract: This work examined the use of eigenvectors in the recognition of binary line-drawn human faces. The use of the eigenvectors as a means of dimension reduction was reviewed. The effectiveness of its application to the recognition and reconstruction of line-drawn faces was demonstrated. A masked version of the human face was used concentrating on the area of the face excluding the hair and face outline. The aspects demonstrated included the effect of reduction of the number of eigenvectors used, comparison between the values of principal components calculated for a foreign set against that from the training set, and the ability of the eigenvectors to reconstruct an occluded member of the training set. The ability of the eigenvectors to reconstruct something not in the training set was investigated. Some possible reasons for the results were discussed. Some ways to implement a library of line-drawn faces for recognition were proposed. It seems that the potential of line-drawn faces in their use for recognition (at least by using the eigenvector approach) is fairly limited both in terms of speed and accuracy, notwithstanding that they can be made more compact to store.

Files in this item

Files Size Format
b14211130.pdf 3.796Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.


Quick Search


More Information