Study Analysis of Human Face Recognition using Principal Component Analysis

Principal Component Analysis (PCA) is a very popular facial recognition method. This research aims to analyze the PCA method, where various scenarios are tested to look for things that affect the results of recognition using this method. There are three datasets used in the testing phase, namely the private dataset, JAFFE, and Yale. The accuracy produced in the private dataset is 79%, 82%, 86%, and 85.33% with a variety of different scenarios, while in the JAFFE dataset the maximum recognition accuracy is 100% and in the last experiment on the Yale dataset, the accuracy is 85.33%. From various experiments that have been done, it is found that the things that affect accuracy are the number of people, training data, attributes used, lighting, and background. While facial expressions and gender do not prove to have a major influence on the recognition process, with a variety of facial expressions, the PCA method can still recognize faces well.