Facial recognition using two-dimensional principal component analysis and k-nearest neighbor: a case analysis of facial images

Abstract

Science and Technology Innovation in Computer Science, especially in the facial image is increasingly needed in the Industrial Era of 4.0. The problem: How to use the working pattern of the Two-Dimensional Principal Component Analysis (2DPCA) method that integrated with K-Nearest Neighbors (KNN) in the Facial Image Recognition for various purposes? The purpose of this study, to analyze the Facial Image Recognition based on the method of Two-Dimensional Principal Component Analysis (2DPCA) which is integrated with KNN. This research uses the method of Two-Dimensional Principal Component Analysis (2DPCA) for the feature extraction process and the KNN classification method is applied to perform the data classification process so that the desired accuracy value is obtained. Research subjects use the image database from UCI repository, consists of 190 black and white face images of people taken with varying pose (straight, left, right, up), expression (neutral, happy, sad, angry), and size. The result of this study is the performance analysis of Facial Image Recognition based on the method of Two-Dimensional Principal Component Analysis (2DPCA) that is integrated with k-Nearest Neighbors (KNN).