Abstract

The human face is frequently used as the biometric signal presented to a machine for identification purposes. Several challenges are encountered while designing face identification systems. The challenges are either caused by the process of capturing the face image itself, or occur while processing the face poses. Since the face image not only contains the face, this adds to the data dimensionality, and thus degrades the performance of the recognition system. Face Recognition (FR) has been a major signal processing topic of interest in the last few decades. Most common applications of the FR include, forensics, access authorization to facilities, or simply unlocking of a smart phone. The three factors governing the performance of a FR system are: the storage requirements, the computational complexity, and the recognition accuracy. The typical FR system consists of the following main modules in each of the Training and Testing phases: Preprocessing, Feature Extraction, and Classification. The ORL, YALE, FERET, FEI, Cropped AR, and Georgia Tech datasets are used to evaluate the performance of the proposed systems. The proposed systems are categorized into Single-Transform and Two-Transform systems. In the first category, the features are extracted from a single domain, that of the Two-Dimensional Discrete Cosine Transform (2D DCT). In the latter category, the Two-Dimensional Discrete Wavelet Transform (2D DWT) coefficients are combined with those of the 2D DCT to form one feature vector. The feature vectors are either used directly or further processed to obtain the persons' final models. The Principle Component Analysis (PCA), the Sparse Representation, Vector Quantization (VQ) are employed as a second step in the Feature Extraction Module. Additionally, a technique is proposed in which the feature vector is composed of appropriately selected 2D DCT and 2D DWT coefficients based on a residual minimization algorithm.

Graduation Date

2018

Semester

Summer

Advisor

Mikhael, Wasfy

Degree

Doctor of Philosophy (Ph.D.)

College

College of Engineering and Computer Science

Department

Electrical Engineering and Computer Engineering

Degree Program

Electrical Engineering

Format

application/pdf

Identifier

CFE0007196

URL

http://purl.fcla.edu/fcla/etd/CFE0007146

Language

English

Release Date

August 2018

Length of Campus-only Access

None

Access Status

Doctoral Dissertation (Open Access)

Share

COinS