Date of Award


Publication Type

Master Thesis

Degree Name



Electrical and Computer Engineering

First Advisor

Majid Ahmadi

Second Advisor

Roberto Muscedere


Electrical engineering, Artificial intelligence




Face recognition is one of the most popular, reliable and widely used applications in real world. It is the main biometric used by humans in many security, law enforcement and commercial systems and high demand of this application attracts researchers from various fields such as image processing, pattern recognition, neural network and computer vision etc. In a Human Face Recognition Systems, we start with pre-processing of the data followed by feature extraction for dimensionality reduction and then classification. In this thesis, neural network classifier with CSD coefficients is used to make the area required for implementation of recognition system more efficient. The FPGA implementation of the proposed technique indicates almost 50% saving in the area required for face recognition application by using neural network classifier with CSD coefficients while the processing speed is improved in comparison to its binary counterpart. Extensive experimental results were conducted to show the utility of the proposed technique.