Design Of Automatic Parking Barrier System With Face Recognition Using Eigenface Method

Abstract

The main problem in this study is that the parking system on the campus of the Catholic University Of Darma Cendika still relies on manual methods, such as the use of cards and physical tickets, which are prone to human error, inefficient, easily misused, and raise security concerns. The main objective of this study is to improve the security and efficiency of parking area management by reducing dependence on card-based methods or physical tickets. This study collects facial data from individuals with various angles and facial positions, then the data is further processed to improve image quality. By applying the Eigenface model, the system is able to recognize faces with 100% accuracy under certain lighting and distance conditions. However, the performance of facial recognition is still affected by the quality of lighting and the distance between the camera and the object, indicating that further optimization is needed. Recommendations proposed include adjusting the lighting and camera position to obtain better facial image results. The Eigenface-based facial recognition technology applied in this study has great potential in improving the efficiency of the automatic parking barrier system. However, to achieve optimal results in various environmental conditions, further development is needed. Thus, it is expected that this system will not only be able to recognize faces accurately, but also be able to operate effectively and efficiently in real environments. In addition, this system also uses the Convolutional Neural Network method to distinguish between real faces and facial images from the cellphone screen, thereby increasing the overall security of the system.