Responsive Banner

Face recognition based on euclidean distance

Harris, Blandin Salama (2017) Face recognition based on euclidean distance. Undergraduate thesis, Universitas Islam Negeri Maulana Malik Ibrahim.

[img] Text (Fulltext)
10650121.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Request a copy

Abstract

ABSTRACT

Face recognition is among the biometrics of choices in many security applications. And, it has many remarkable and important abilities that people use in their everyday lives. The purpose of the current study consits in evaluating, the accuracy, precision, recall, F-measure, and the effectiveness of Face recognition.
Several technics could be used for a facial recognition nowadays. People could adopt the technic of geometrical feature, photometric, elastic face matching approach or the neutral networks approach. But in this study we are look at the face recognition based on Euclidean distance approach.

Face recognition Based on Euclidean distance is a part of the geometrical feature approach, in which the applications match the Euclidean distance obtained from the coordinates of facial features.

Throughout the data analysis, we have found out that the face recognition with just four images selected from the database has brought the best results with a very high F-meaure at 81.88%. The application has shown the effectiveness for 27.9 seconds.

But further research is needed in future to explore a more efficient technic to extract the coordinates of facial features.

Item Type: Thesis (Undergraduate)
Supervisor: Crysdian, Cahyo and Holle, Khadijah Fahmi Hayati
Keywords: Face Recognition; geometrical feature; Euclidean distance; coordinate facial feature
Departement: Fakultas Sains dan Teknologi > Jurusan Teknik Informatika
Depositing User: Koko Prasetyo
Date Deposited: 27 Jun 2023 10:47
Last Modified: 27 Jun 2023 10:47
URI: http://etheses.uin-malang.ac.id/id/eprint/51095

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item