IMPLEMENTASI DEEP LEARNING MENGGUNAKAN CNN UNTUK SISTEM PENGENALAN WAJAH

Abstract

Face recognition system is generally divided into two stages, face detection system, which is a pre-processing step followed by a facial recognition system. This step will quickly be done by humans but it takes a long time for the computer. This ability of humans is what researchers want to duplicate in the last few years as biometric technology in computer vision to create a model of face recognition in computer. Deep learning becomes a spotlight in developing machine learning, the reason because deep learning has reached an extraordinary result in computer vision. Based on that, the author came up with an idea to create a face recognition system by implementing deep learning using the CNN method and applying library openFace. The CNN methods are still superior and widely used because they have good accuracy. The initial process was taking a picture of the face to be used as a dataset. From this dataset, face preprocessing will be carried out, that is, to extract the facial vector features into 128-d and to classify the facial vector. The contribution of this research is the addition of features to improve the accuracy of the facial recognition system using the CNN method. The results of this research get a precision value of 98.4%, a recall of 98% and an accuracy of 99.84%.