Sistem Biometrik Pengenalan Wajah

Abstract

Biometric security system can recognize its user more precisely than password- based security systems. The biometrics have characteristics like not easily lost, can’t be forgotten, and not easily counterfeited because its existence inherent in human beings. There are several different types of security by using biometric technologies including fingerprint recognition, eye retina, and facial structure. In this study, the authors have developed a face recognition into real-time security system for the entrance. This research uses a webcam to capture the image of the user’s face and then compared with the face that stored in the database. Generally, there are two methods used by the author which is HaarCascade method for face detection and PCA or Eigenface method for face recognition. Experiments were done using 150 training data and 150 test data. In this system, 30 cm were used as parameters of distance to measure the accuracy. The results showed overall recognition success rate of 83.33%. This system is designed to work in real-time with the hope to make it easier for the user and can minimize criminal act in the future.