PENGENALAN EKSPRESI WAJAH UNTUK SISTEM KEAMANAN BERBASIS CNN

ABDILLAH, RAHMAD RHEDO and Husin, Zaenal (2019) PENGENALAN EKSPRESI WAJAH UNTUK SISTEM KEAMANAN BERBASIS CNN. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_20201_03041181520012.pdf] Text
RAMA_20201_03041181520012.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_TURNITIN.pdf] Text
RAMA_20201_03041181520012_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_01_front_ref.pdf]
Preview
Text
RAMA_20201_03041181520012_0014025604_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (767kB) | Preview
[thumbnail of RAMA_20201_03041181520012_0014025604_02.pdf] Text
RAMA_20201_03041181520012_0014025604_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (542kB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_03.pdf] Text
RAMA_20201_03041181520012_0014025604_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (20kB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_04.pdf] Text
RAMA_20201_03041181520012_0014025604_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (365kB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_05.pdf] Text
RAMA_20201_03041181520012_0014025604_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10kB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_06_ref.pdf] Text
RAMA_20201_03041181520012_0014025604_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (79kB) | Request a copy
[thumbnail of RAMA_20201_03041181520012_0014025604_07_lamp.pdf] Text
RAMA_20201_03041181520012_0014025604_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (216kB) | Request a copy

Abstract

Face is one of biometrics that can be utilized to identify an individu through facial recognition and facial expressions. Many studies have discussed the usage of face as biometrics. However, many of them had low accuracy and not many studies have discussed face recognition using different expressions. Thus, this study focuses on these problems using the Convolutional Neural Network (CNN) method. Total data were obtained from 16,640 photos with 4 facial expressions (normal, smile, surprise, and anger) from 52 students of Electrical Engineering University of Sriwijaya. These data were taken in outdoor conditions (afternoon and evening) and indoor conditions using a webcam. 2 types of CNN architecture, namely simple architecture of CNN and CNN-VGG model VGG-f architecture are utilized. The result showed that a simple CNN architecture has problems with overfitting and underfitting and these can be overcome the VGG-f model architecture. The testing result showed that the method could achieve accuracy rate of 100% in face recognition and 99,9% in facial expression recognition, respectively. Error in recognition might be caused by images that are similar to other images

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Convolutional Neural Network (CNN), Pengolahan Citra, Pengenalan Wajah, Pengenalan Ekspresi Wajah, VGG-f.
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1-9971 Electrical engineering. Electronics. Nuclear engineering > TK1 Electrical engineering--Periodicals. Automatic control--Periodicals. Computer science--Periodicals. Information technology--Periodicals. Automatic control. Computer science. Electrical engineering. Information technology.
Divisions: 03-Faculty of Engineering > 20201-Electrical Engineering (S1)
Depositing User: Users 2747 not found.
Date Deposited: 29 Oct 2019 01:35
Last Modified: 29 Oct 2019 01:35
URI: http://repository.unsri.ac.id/id/eprint/13584

Actions (login required)

View Item View Item