Validation of the Haar Cascade Classification Method in Face Detection

Abstract

As technology develops, faces are used as a tool for human interaction with computers for security systems. Face detection technology can also provide convenience to users in various fields, especially security systems. However, there are problems regarding accuracy, complexity in the face recognition process so that many methods have been developed to increase the accuracy and complexity of the face detection process. This study aims to validate the haar cascade classification method in detecting faces from various shooting angles, with a distance of one meter from the camera and the respondent is free to make movements as well as various facial expressions and various lighting conditions that are different for each respondent. The results of this study found that the haar cascade classification method showed that the higher the epoch value, the lower the mean square error (MSE). This study also found that the haar cascade classification method has good accuracy for detecting faces from various angles, different lighting and different facial expressions with a maximum distance of one meter from the camera. This study provides recommendations for making face recognition applications using the haar cascade classification method because it can be used well for lighting effects, facial expressions and a maximum shooting distance of one meter.