• العربية
    • English
  • English 
    • العربية
    • English
  • Login
Home
Publisher PoliciesTerms of InterestHelp Videos
Submit Thesis
IntroductionIUGSpace Policies
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  •   Home
  • Faculty of Engineering
  • Staff Publications- Faculty of Engineering
  • View Item
  •   Home
  • Faculty of Engineering
  • Staff Publications- Faculty of Engineering
  • View Item

Please use this identifier to cite or link to this item:

http://hdl.handle.net/20.500.12358/27448
TitleDeep Learning HMM Versus Multi-resolution transforms for Soft biometric estimation
Title in Arabicالتعلم العميق لنموذج ماركوف الخفي مقابل تحويلات متعددة الدقة لتقدير السمات البيومترية
Abstract

This work is to introduce two different methodologies to estimate the soft biometric traits from face image. The first proposed methodology to extract effective features from facial images using two multi-resolution transforms; waveatom and shearlet, for estimating gender, ethnicity, facial expression and age by Artificial Neural Network (ANN). And the second proposed methodology to use deep learning to extract suitable features by double convolutional and pooling layers to feed Hidden Markov Model (HMM) for classification. To achieve the comparative study, our experiments carried out on a large database collected from three different databases: US Adult Faces, Extended CohnKanade and FG-NET databases. The experimental results show that the multi-resolution waveatom transform was more effective than shearlet transform, but HMM with Deep learning were the best performance and more robust method to classify multi objects together such as in this paper to estimate 13 soft biometrics which clustering in four categories

Authors
Alhanjouri, Mohammed A.
El-Samak, Ahmad Fouad
TypeConference Paper
Date2018-10-01
LanguageEnglish
Subjects
Waveatom transform
Shearlet transform
Artificial Neural Network
Hidden Markov Model
Deep Learning
Published inInternational Conference on Data Science, E-learning and Information Systems
PublisherUDIMA Universidad a Distancia de Madrid
Citation
Item linkItem Link
License
Collections
  • Staff Publications- Faculty of Engineering [1035]
Files in this item
Paper-Data'18.pdf756.1Kb
Thumbnail

The institutional repository of the Islamic University of Gaza was established as part of the ROMOR project that has been co-funded with support from the European Commission under the ERASMUS + European programme. This publication reflects the views only of the author, and the Commission cannot be held responsible for any use which may be made of the information contained therein.

Contact Us | Send Feedback
 

 

Browse

All of IUGSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsSupervisorsThis CollectionBy Issue DateAuthorsTitlesSubjectsSupervisors

My Account

LoginRegister

Statistics

View Usage Statistics

The institutional repository of the Islamic University of Gaza was established as part of the ROMOR project that has been co-funded with support from the European Commission under the ERASMUS + European programme. This publication reflects the views only of the author, and the Commission cannot be held responsible for any use which may be made of the information contained therein.

Contact Us | Send Feedback