Please use this identifier to cite or link to this item:
Title: Weightless neural networks for face recognition
Authors: Khaki, Kazimali M
Advisors: Stonham, J
Dear, I
Keywords: Image texture mapping;Ranking algorithm;Face recognition with wisard;Effect of zoom, liaghting and image size on neural network;Real time face recognition
Issue Date: 2013
Publisher: Brunel University School of Engineering and Design PhD Theses
Abstract: The interface with the real-world has proved to be extremely challenging throughout the past 70 years in which computer technology has been developing. The problem initially is assumed to be somewhat trivial, as humans are exceptionally skilled at interpreting real-world data, for example pictures and sounds. Traditional analytical methods have so far not provided the complete answer to what will be termed pattern recognition. Biological inspiration has motivated pattern recognition researchers since the early days of the subject, and the idea of a neural network which has self-evolving properties has always been seen to be a potential solution to this endeavour. Unlike the development of computer technology in which successive generations of improved devices have been developed, the neural network approach has been less successful, with major setbacks occurring in its development. However, the fact that natural processing in animals and humans is a voltage-based process, devoid of software, and self-evolving, provides an on-going motivation for pattern recognition in artificial neural networks. This thesis addresses the application of weightless neural networks using a ranking pre-processor to implement general pattern recognition with specific reference to face processing. The evaluation of the system will be carried out on open source databases in order to obtain a direct comparison of the efficacy of the method, in particular considerable use will be made of the MIT-CBCL face database. The methodology is cost effective in both software and hardware forms, offers real-time video processing, and can be implemented on all computer platforms. The results of this research show significant improvements over published results, and provide a viable commercial methodology for general pattern recognition.
Description: This thesis was submitted for the degree of Doctor of Philosophy and awarded by Brunel University.
Appears in Collections:Electronic and Computer Engineering
Dept of Electronic and Computer Engineering Theses

Files in This Item:
File Description SizeFormat 
FulltextThesis.pdf6.4 MBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.