A new approach for real time face recognition system using a modified eigenfaces with edge tracking

Other Title(s)

نهج جديد للتعرف على الوجوه في الوقت الحقيقي بواسطة (Eigenfaces)‎ المعدلة و تتبع الحافه

Dissertant

Maraqah, Randah Muhammad Sharif

Thesis advisor

Tamimi, Abd al-Fattah Arif

Comitee Members

Abu Jassar, Radwan
Hirz Allah, Nail B.

University

Middle East University

Faculty

Faculty of Information Technology

Department

Department of Computer Information Systems

University Country

Jordan

Degree

Master

Degree Date

2014

English Abstract

This thesis presents Real-time Face Recognition using modified Eigenfaces technique and color segmentation with Edge tracking for face detection.

Eigenfaces is a fast and simple method for face recognition which is considered as a remarkable feature for eigenfaces, but the face recognition accuracy drops severely when head position changes which needs to feed the training set with large number of face images in different head position.

Proposed approach in this thesis intent to implement eigenfaces technique with skin color segmentation and Hough transforms edge detection and tracking to enhance the results of face recognition in different head position, face profile and head scale.

This will be implemented with a data set that have only three images for each individual, images will have unconstrained background for different environments for any given image to find the face and recognize the person in the image, where unconstrained background increase the complexity of the detection and recognition process, that requires these condition must be solved for real time implementation.

Results have been showed that increasing of both number of training images and the number of individuals in the sub-set group (found that) was three training images per each, and three individuals for each sub-set group which is found as the optimal choice training for this approach.

Comparison with standard dataset of faces has been done for verifying proposed work assumption; results were fair and approving for developed work.

Main Subjects

Information Technology and Computer Science

No. of Pages

107

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-694274