Please use this identifier to cite or link to this item:
Title: A face recognition system : a novel non-negative matrix factorization based approach
Authors: Khnayzir, John
Abboud, Elie
Advisors: Ishak, Dany
Issue Date: 2019
Nowadays, face recognition has become an important topic in the field of biometric authentication. In this context, many researchers have worked on improving the reliability of face recognition systems and several methods were developed for this purpose. This project presents a new approach for face recognition using the Non-Negative Matrix Factorization. The overall proposed approach is implemented using Python. In addition, the results of the developed approach are compared with other approaches which are also implemented in this work. Finally, a hybrid approach was developed using the combination of multiple approaches. The comparison is performed using the Euclidean Distance and Correlation Coefficient for classification. The results show that the performance of the proposed approach and the hybrid approach are much better that the other techniques.
Includes bibliographical references (p. 60-61).

Supervised by Dr. Dany Ishak.
Rights: This object is protected by copyright, and is made available here for research and educational purposes. Permission to reuse, publish, or reproduce the object beyond the personal and educational use exceptions must be obtained from the copyright holder
Ezproxy URL: Link to full text
Type: Project
Appears in Collections:UOB Theses and Projects

Show full item record

Record view(s)

checked on May 5, 2021

Google ScholarTM


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