Curvelet and Waveatom Transforms Based Feature Extraction for Face Detection

Hanjouri, Mohammed (2011) Curvelet and Waveatom Transforms Based Feature Extraction for Face Detection. Al-Aqsa University Journal (Natural Sciences Series), 15 (1). pp. 41-66. ISSN ISSN 2070-3155 (Print), ISSN 2521-893X (Online)

[img]
Preview
Text
محمد الحنجوري3.pdf - Published Version

Download (659kB) | Preview
Official URL: https://scholar.alaqsa.edu.ps

Abstract

This work identifies two novel techniques for Face Features Extraction based on two different multiresolution analysis tools; the first called Curvelet transform while the second is Waveatom Transform. The resultant features are trained and tested via two famous classifiers; one of them is the Artificial Neural Network (ANN) and the other is Hidden Markov Model (HMM). Experiments are carried out on two well-known datasets; AT&T dataset consists of 400 images corresponding to 40 people, and Essex Grimace dataset consists of 360 images corresponding to 18 people. Experimental results show the strength of both Curvelets and Waveatom features. In one hand, Waveatom features obtained the highest accuracy rate of 94% and 96% with HMM classifier, and 90% and 93% with ANN classifier, for AT&T and Essex Grimace datasets, respectively. In the other hand, two levels Curvelet features achieved accuracy rate of 92% and 95% with HMM classifier, and 88% and 92% with ANN classifier, for AT&T and Essex Grimace datasets, respectively. A comparative study for waveatom with wavelet-based, curvelet-based, and traditional Principal Component Analysis (PCA) techniques is also presented. The proposal techniques supersede all of them. And proves the robustness of feature extraction methods used against extreme variation on expression and illumination, and different facial details. Also, indicates the potential of HMM over ANN, as they are classifiers.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > TR Photography
Divisions: Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User: Mr. Ahmed A, Ouda
Date Deposited: 16 Jan 2018 11:38
Last Modified: 16 Jan 2018 11:38
URI: http://scholar.alaqsa.edu.ps/id/eprint/51

Actions (login required)

View Item View Item