Date of Award


Publication Type

Master Thesis

Degree Name



Electrical and Computer Engineering

First Advisor

Wu, Jonathan


Applied sciences, Computier vision, Embadded face recognition, Embedded system, Facerecognition, Lbp, Sparse face recognition




Facial recognition from an image or a video sequence draws attention for many image processing researchers owing to its myriad applications in real world as well as in computer vision, human-computer interaction and intelligent systems. Facial structures have unique features which can be extracted using some mathematical tools. We have used Principal Component Analysis (PCA) and Local Binary Pattern (LBP) to extract them and stored them in a database. When the query image is given the facial features are extracted and compared to the previously obtained results using Sparse Face recognition. Detailed test methods have been defined and an extensive testing of the algorithm has been performed on various standard databases. The results have been tabulated with required graphs. The proposed algorithm has been compared to other different algorithms which show significant improvement in results with small number of training samples. Finally the algorithm was integrated in a hardware system so that it can be used as a self sufficient portable system.