SISTEM KEAMANAN BERBASIS CNN MENGGUNAKAN IRIS MATA YANG DINORMALISASI DENGAN DAUGMAN RUBBER SHEET MODEL

EKAYANSYAH, RIZKY ATHIYYAH and Hikmarika, Hera and Dwijayanti, Suci (2022) SISTEM KEAMANAN BERBASIS CNN MENGGUNAKAN IRIS MATA YANG DINORMALISASI DENGAN DAUGMAN RUBBER SHEET MODEL. Undergraduate thesis, Sriwijaya University.

	Text RAMA_20201_03041181621029.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
Preview	Text RAMA_20201_03041181621029_0007127801_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_20201_03041181621029_0007127801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (856kB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (148kB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (80kB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (494kB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_20201_03041181621029_0007127801_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy

Abstract

The eye iris is a biometric that has a pattern that requires high accuracy to be identified. Problems that occur are generally image quality, because if the quality of the image used is not good, such as low resolution, blurring, or unusual luster, it will cause difficulty in distinguishing between the iris and pupil. Therefore, the Daugman Rubber Sheet Model method was used to increase the accuracy of the identification results. The Daugman Rubber Sheet method is also popular among researchers who discuss the identification of the iris. The data used in this study used primary data as many as 14 individuals and secondary data as many as 44 individuals. The CNN architectural models used are VGG16, ResNet50, ResNet101, MobileNetV2, MobileNetV3, DenseNet121, DenseNet169, and IrisNet. From the classification results in the study, the Daugman Rubber Sheet Model method has a good effect on improving the classification of the iris image. However, the results were not significantly different with the non-normalized iris. It can be seen from the comparison of the results of the classification of normalized and non-normalized data, which have almost the same high accuracy with a difference of about 1%. The best CNN architectural models used are DenseNet, ResNet, and IrisNet because they have the best performance for identifying the iris with an accuracy of 99%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Iris Recognition, Daugman Rubber Sheet Model, CNN, VGG16, ResNet, MobileNet, DenseNet, IrisNet, Canny Edge
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:	Rizky Athiyyah Ekayansyah
Date Deposited:	31 Jan 2022 07:07
Last Modified:	31 Jan 2022 07:07
URI:	http://repository.unsri.ac.id/id/eprint/63880

Actions (login required)

View Item