�PENGENALAN WAJAH DENGAN METODE PRINCIPAL COMPONENT ANALYSIS (PCA) PADA SISTEM ABSENSI REAL-TIME

• Main Authors: , Abdul Jabbar Febianto, , Teguh Bharata Adji, S.T., M.T., M.Eng., Ph.D.
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2012
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/100583/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=57040
• Institution: Universitas Gadjah Mada

In information technology, biometrics system is a system that refers to technologies for measuring and analyzing human body characteristics. body parts such as fingerprints, retina, eye, voice patterns and facial patterns, are examples of body parts that can be used to process otenfikasi. Facial recognition technology increasingly used and developed with a very wide range of applications, such as security systems, access control systems area, and student attendance system. This research presents a biometrics attendance system that applies the identification of facial recognition techniques. The system is focused on the design of attendance system that works by detecting faces in real-time, natural, dynamic and automatic without any manual process, with the aim that students do not know the ongoing process of absenteeism, it should not interfere with the learning process. The system is implemented on a lecture at the university. This system has two stages of the process of absenteeism, the first process of detecting every face that passes through the entrance of the room to get a facial image, the second is to do facial recognition on the face image is detected to determine the presence. The system uses an IP-Camera to detect the faces of students. These systems apply the Viola-Jones algorithm for face detection technique and the method of Principal Component Analysis (PCA) for face recognition techniques to obtain eigenface from each facial image. The results from this research suggest the accuracy rate of 79% of face recognition. These results were obtained by performing 100 trials of 100 facial images consisting of 10 students and each student has 10 face images.