PENGGUNAAN FITUR FACE TRACKING DENGAN METODE KANADE-LUCAS-TOMASI PADA E-READER BERBASIS MOBILE

IDHAM, MUHAMMAD and Samsuryadi, Samsuryadi and Miraswan, Kanda Januar (2018) PENGGUNAAN FITUR FACE TRACKING DENGAN METODE KANADE-LUCAS-TOMASI PADA E-READER BERBASIS MOBILE. Undergraduate thesis, Sriwijaya University.

Preview	Text RAMA_55201_09021081319001_0004027101_0009019002_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021081319001_0004027101_0009019002_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (457kB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (77kB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (83kB) | Request a copy
	Text RAMA_55201_09021081319001_0004027101_0009019002_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (220kB) | Request a copy

Abstract

Kanade-Lucas-Tomasi(KLT) is a feature point tracking-based feature extraction method on Computer Vision scope. The use of the KL T method as it may be implemented on Face Tracking by using face movements left and right as page navigation in e-reader. Face Tracking with KL T was supported by face detection using the Viola-Jones method. The KL T method is used because the image color comparison method has a weakness in the low-lighting environment and depends on the background state of the object. The results of previous studies indicate that the KLT method has a detection rate of up to 91 % in bright and lowlight conditions. From the test results obtained after being implemented in the ereader, the accuracy of the responsiveness of the KL T method used as page navigation based on testing between 94%--96%, both under normal circumstances, wood background, and low lighting.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Computer Vision, Kanade-Lucas-Tomasi, Face Tracking, Viola-Jones
Subjects:	R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Mrs Sri Astuti
Date Deposited:	02 Oct 2019 02:21
Last Modified:	02 Oct 2019 02:21
URI:	http://repository.unsri.ac.id/id/eprint/9962

Actions (login required)

View Item