Open AccessLecturer Attendance System using Face Recognition Application an Android-Based
Author(s) -
Feri Susanto,
Fauziah Fauziah,
Andrianingsih Andrianingsih
Publication year - 2021
Publication title -
journal of computer networks, architecture and high performance computing
Language(s) - English
Resource type - Journals
ISSN - 2655-9102
DOI - 10.47709/cnahpc.v3i2.981
Subject(s) - facial recognition system , computer science , histogram , eigenface , android (operating system) , local binary patterns , attendance , face detection , artificial intelligence , machine learning , pattern recognition (psychology) , data mining , image (mathematics) , operating system , economic growth , economics
In the field of industries, businesses, and offices the use of security systems and administrative management through data input using a face recognition system is being developed. Following the era of technological advances, communication and information systems are widely used in various administrative operational activities and company security systems because it is assessed by using a system that is based on facial recognition security levels and more secure data accuracy, the use of such systems is considered to have its characteristics so it is very difficult for other parties to be able to engineer and manipulate data produced as a tool to support the company's decision. Related to this, causing the author is to try to research the detection of facial recognition that is present in the application system through an Android device, then face recognition detection will be connected. and saved to the database that will be used as data about the presence of teaching lecturers. Using the local binary pattern histogram algorithm method to measure the face recognition system that can be applied as a technique in the attendance system of lecturers to be more effective and efficient. Based on testing by analyzing the false rate error rate and the false refusal rate can be seen that the average level of local binary pattern histogram accuracy reaches 95.71% better than through the Eigenface method which is equal to 76.28%.