الفهرس 
Different facial expressionOnly 14 pages are availabe for public view
 |  | from | 149 |  |  |
| | | from | 149 | | |
Abstract
The great increase of computational software resources in the last decade has provided the computers with the means to solve many computer vision tasks like like object tracking and recognition.The great increase of computational software resources in the last decade has provided the computers with the means to solve many computer vision tasks like object tracking and recognition. Within these tasks, face detection of humans occupy one of the most important roles. Automatic human face detection from images in surveillance and biometric applications is a challenging task due to the variances in image background, view, illumination, articulation, and facial expression. Recognition of human faces is useful in any user identification system or face database management.
Detection of face humans can be used as a initializing step to human motion, lip, or gestures tracking, as a localization step for face recognition as well as for image databases queries.
The purpose of this research is to study various techniques for face detection and face recognition and compare their performance by implementing them, then investigate the possible improvements on these techniques increase their efficiency or to find new technique that has more advantages such as reduce the execution time and its flexibility. In this way, the objective of this thesis is obtained by proposed new algorithm in face detection, and another algorithm of face recognition Chapter 1 presents the motivation behind this thesis and defined the fundamental problem considered with real applications. It also summarized the contributions made toward this problem.
Chapter 2 presents a brief study of the fundamental concepts of the face detection operation and definitions related to color spaces behind different skin and face detectors. Some of face detection techniques based on color models are described.
Chapter 3 introduces a proposed new algorithm that can detect human faces from an image, skin color as a tool for detection with different filtering steps, using Template Matching. The proposed algorithm performance compared to the previous methods, such as Zahra, and Viola-Jones techniques. Numerical results underline the robustness of the presented approach for tested images of faces which have a specific complexion varying under certain range are shown.
Chapter 4 describes some basic definitions of face recognition. We study the face recognition algorithms such as Principal Component Analysis(PCA), Independent Component Analysis (ICA), Multilinear Principal Component Analysis (MPCA) and Linear Discriminant Analysis (LDA). Neural networks with Gabor filters, Neural networks and Hidden Markov Models, and Fuzzy neural networks have been discussed.
Chapter 5 presents a new approach for face recognition based on similarity measure method. In addition, We apply various measure classes to increase the efficiency of the proposed method. Experimental results show that these similarity measures can give an useful way for measuring the similarity between fuzzy sets for face recognition.
Chapter 6 summarizes the highlights and the results of this thesis and presents some open problems.