Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model

In this research study, the performance of the real-time face recognition system with machine learning, as well as the performance of each Haarcascade classifier based on accuracy and speed were investigated. The subset of machine learning called deep learning was employed in the real-time face reco...

Full description

Saved in:

Bibliographic Details
Main Author:	Sukri, Syazwan Syafiqah
Format:	Thesis
Language:	English
Published:	2021
Subjects:	QA75.5-76.95 Electronic computers Computer science
Online Access:	http://eprints.usm.my/52727/1/SYAZWAN%20SYAFIQAH%20BINTI%20SUKRI.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.52727
record_format	uketd_dc
spelling	my-usm-ep.527272022-06-02T03:24:42Z Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model 2021-05 Sukri, Syazwan Syafiqah QA75.5-76.95 Electronic computers. Computer science In this research study, the performance of the real-time face recognition system with machine learning, as well as the performance of each Haarcascade classifier based on accuracy and speed were investigated. The subset of machine learning called deep learning was employed in the real-time face recognition system as the deep face recognition technology has improved the state-of-the-art performance. A pre-trained model named FaceNet was used and the triplet loss technique was employed to impose a margin between every pair of faces from the same person to other faces. In other words, it minimizes the distance between the anchor and the positive from the same identity and maximizes the distance between the anchor and the negative from different identities. Furthermore, the performance of the system was further investigated by implementing the Tensorflow framework to improve the system performance by the usage of the Graphics Processing Unit (GPU). Labeled Faces in Wild (LFW) dataset was used as the benchmark to test the performance of the face recognition system. Furthermore, a preliminary experiment was conducted to evaluate the performance of Haarcascade classifiers so that the best classifier can be chosen in terms of accuracy and speed. It was found that haarcascade frontalface default exhibited the best performance compared to haarcascade frontal face alt and haarcascade frontalface alt2 with accurate number of faces detected and shortest average time taken to detect faces. 2021-05 Thesis http://eprints.usm.my/52727/ http://eprints.usm.my/52727/1/SYAZWAN%20SYAFIQAH%20BINTI%20SUKRI.pdf application/pdf en public masters Perpustakaan Hamzah Sendut Pusat Pengajian Sains Komputer
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QA75.5-76.95 Electronic computers Computer science
spellingShingle	QA75.5-76.95 Electronic computers Computer science Sukri, Syazwan Syafiqah Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
description	In this research study, the performance of the real-time face recognition system with machine learning, as well as the performance of each Haarcascade classifier based on accuracy and speed were investigated. The subset of machine learning called deep learning was employed in the real-time face recognition system as the deep face recognition technology has improved the state-of-the-art performance. A pre-trained model named FaceNet was used and the triplet loss technique was employed to impose a margin between every pair of faces from the same person to other faces. In other words, it minimizes the distance between the anchor and the positive from the same identity and maximizes the distance between the anchor and the negative from different identities. Furthermore, the performance of the system was further investigated by implementing the Tensorflow framework to improve the system performance by the usage of the Graphics Processing Unit (GPU). Labeled Faces in Wild (LFW) dataset was used as the benchmark to test the performance of the face recognition system. Furthermore, a preliminary experiment was conducted to evaluate the performance of Haarcascade classifiers so that the best classifier can be chosen in terms of accuracy and speed. It was found that haarcascade frontalface default exhibited the best performance compared to haarcascade frontal face alt and haarcascade frontalface alt2 with accurate number of faces detected and shortest average time taken to detect faces.
format	Thesis
qualification_level	Master's degree
author	Sukri, Syazwan Syafiqah
author_facet	Sukri, Syazwan Syafiqah
author_sort	Sukri, Syazwan Syafiqah
title	Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
title_short	Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
title_full	Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
title_fullStr	Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
title_full_unstemmed	Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model
title_sort	improvement of facial recognition accuracy using eye-lids movement and tensorflow model
granting_institution	Perpustakaan Hamzah Sendut
granting_department	Pusat Pengajian Sains Komputer
publishDate	2021
url	http://eprints.usm.my/52727/1/SYAZWAN%20SYAFIQAH%20BINTI%20SUKRI.pdf
_version_	1747822207426363392

Improvement Of Facial Recognition Accuracy Using Eye-Lids Movement And Tensorflow Model

Similar Items