Designing and Implementing a Multi-View Face Recognition System

Please enable javascript in your browser.

Shoja Ghiass, Reza | 2009

685 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 39307 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Fatemizadeh, Emadoddin; Marvasti, Farrokh
Abstract:
This thesis presents a novel approach for detection and recognition of multi-view faces whose location is unknown and the illumination conditions are varying. The illumination is a big problem in the face detection and recognition aspects. Two completely different methods are proposed for face detection in this thesis. Our proposed methods do not use the skin colour information for face detection. The detection of faces is accomplished after cancelling the effect of the various illumination conditions. Because of the independency of the approaches to the face’s skin colour, persons with every kind of skin colours are detected even in completely dark environments. Next, the detected faces are recognized. The experiments have shown that we can combine some proposed aspects of feature based methods with eigenface method and get successful results. The illumination dependency and scaling problems of eigenface method have also been solved by a new methodology in this thesis
Keywords:
Fuzzy Logic ; Illumination Method ; Face Detection ; Face Recognition

No TOC