Gavrilova, MarinaZohra, Fatema Tuz2018-01-182018-01-182017-12-20http://hdl.handle.net/1880/106266Quality assessment of a biometric sample is relatively difficult and understudied problem compared to the automated recognition and feature extraction in biometrics. More attention should be directed towards this problem since it has been found in many studies that the quality of samples significantly affects the performance of a biometric system. This thesis focuses on designing a unified framework which can adaptively compensate for different quality degradations of the facial images. The proposed quality estimation model determines the overall quality of a facial sample by considering the impact of quality degradation on the performance of the sample. Our proposed quality-based face recognition system utilizes this overall quality score to determine the appropriate preprocessing steps and facial representations for improved recognition performance. The proposed methodology employs a quality-based weighted score fusion to boost the recognition performance further. Extensive experiments with real and synthetic samples demonstrate the effectiveness of the proposed methodology.enUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.Applied SciencesComputer Sciencemaster thesis10.11575/PRISM/5347