Penerapan Estimasi Posisi Dan Tracking Wajah Pada Sistem Presensi Mahasiswa

Afrillebar, Putra Pratama (2020) Penerapan Estimasi Posisi Dan Tracking Wajah Pada Sistem Presensi Mahasiswa. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

Preview	Text ABSTRACT.pdf - Accepted Version Download (503kB) | Preview
Preview	Text ABSTRAK.pdf - Accepted Version Download (503kB) | Preview
Preview	Text COVER.pdf - Accepted Version Download (3MB) | Preview
Preview	Text BAB 1.pdf - Accepted Version Download (704kB) | Preview
Preview	Text BAB 2.pdf - Accepted Version Download (970kB) | Preview
Preview	Text BAB 3.pdf - Accepted Version Download (1MB) | Preview
	Text BAB 4.pdf - Accepted Version Restricted to Registered users only Download (1MB)
Preview	Text BAB 5.pdf - Accepted Version Download (641kB) | Preview
Preview	Text DAFTAR PUSTAKA.pdf - Accepted Version Download (520kB) | Preview

Abstract

The current presence system can be done with a computerized system, one of which is the facial biometric system. There is a problem with the automatic presence system that implements the facial recognition process, namely user intervention. The user intervention that occurs is the mistake of the tracking process in carrying out facial recognition because there are two or more people who are coinciding with each other or have a close distance between one person and another in a two�dimensional (2D) image. This problem can be solved with the clustering method and can be optimized by estimating the face position by transforming 2D face position data into a three�dimensional (3D) form. The process of clustering and estimating the face position produces a position mapping that can reduce user intervention in an automatic presence system. This study focuses on the application of clustering-based position estimation and tracking to people's faces so that the three-dimensional position is located. Position estimation can be obtained by creating a ready-to-use kernel for predicting the three-dimensional coordinates of a face based on the two�dimensional coordinates of the two images. Position estimation can be done by utilizing the Machine Learning algorithm family. In this study, the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm was used. Meanwhile, the clustering in this study uses the K-Means algorithm. Based on the test results, it was found that the kernel error in estimating the location of the face was 9.61 cm. The accuracy of tracking an object based on clustering is 100%. Keywords: K-Means; LASSO; Machine Learning; Object Tracking; Position Estimation

Actions (login required)

View Item