FACE RECOGNITION ATTENDANCE SYSTEM USING CNN

Sayudha, Brian (2022) FACE RECOGNITION ATTENDANCE SYSTEM USING CNN. Diploma thesis, Politeknik Negeri Malang.

	Text Cover.pdf Download (893kB)
	Text BAB I.pdf Download (107kB)
	Text BAB IV.pdf Download (982kB)
	Text BAB II.pdf Download (520kB)
	Text BAB III.pdf Download (158kB)
	Text BAB V.pdf Download (5MB)
	Text BAB VI.pdf Download (493kB)
	Text BAB VII.pdf Download (90kB)
	Text DAFTAR PUSTAKA.pdf Download (163kB)

Abstract

In the process of recording attendance at an event, event organizer generally still uses the traditional method of using paper as a medium to record attendance at each event. With this traditional method, there are still many shortcomings in terms of security, and management, even with the traditional method the event organizers do not know when participants attend. In terms of security, the traditional attendance system is still quite lacking. Because many participants cheated by ‘titip absen’. For example, copied signatures, or attendance checks can still be tricked because participants can change them easily. Of course, this can hinder the success of an event with certain attendance rules. Therefore, it is necessary to have an attendance system that can be carried out efficiently, safely, and easily to be managed. With attendance made online or by using a smartphone, it can make it easier for event organizers to manage the traces of participants' attendance. Online attendance can significantly reduce the use of paper and increase the security of the attendance system. Security can be added with biometric authentication which will use the face as a participant identification medium which can reduce fraud such as 'taking in absentia' which is often done in Indonesia today. Thus, face recognition certainly requires the newest and fastest method, making it easier for event organizers and participants to attend certain events. From this, the research was conducted by choosing the CNN (Convolutional Neural Network) method as the basis for facial recognition in the attendance system. CNN method is an artificial neural network that is more often used in visual image analysis. This method is used as a face recognition method because it can distinguish visual images from one another with various aspects given and gives fairly accurate results even though they are given quite a bit of information or training data. Furthermore, face recognition research using the CNN method produces the highest accuracy with a percentage of 100% and the lowest is 20%. By experimenting with 15 different poses and using various accessories for each volunteer. And has a total accuracy of 67% for advanced and 47% for basic. From this, it can be concluded that the CNN method is quite accurate when given 1 training data with a total of 15 poses for each volunteer.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Attendance system, Smartphone, biometrics, face recognition, CNN
Subjects:	A Computer Science > Artificial Intelligence A Computer Science > Applied Computer Science
Divisions:	Jurusan Teknologi Informasi > Teknik Informatika
Depositing User:	Brian Sayudha
Date Deposited:	14 Mar 2024 03:24
Last Modified:	14 Mar 2024 03:24
URI:	http://repota.jti.polinema.ac.id/id/eprint/905

Actions (login required)

View Item