KLASIFIKASI EMOSI PADA WAJAH DARI REKAMAN APLIKASI VIDEO CONFERENCE DENGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

Abstract

The COVID-19 pandemic has now become a very heartbreaking disaster for all inhabitants of the earth. All activities and life are certainly disrupted due to this epidemic. Education is also one of the areas that is hampered, all levels of education from TK, SD, SMP, and SMA, while in college must carry out the teaching and learning process online. By controlling emotions, it can have a good impact on controlling one's emotional intelligence. Humans generally have 2 ways of expressing their emotions, namely verbally and nonverbally. Verbal ability is to express everything that is felt consciously in words, while nonverbal ability is to express what the body feels using media on the body, such as hand movements, shrugging, facial expressions, and others. This system will classify emotions from facial expressions using the CNN method and face detection using the Viola-Jones method. Viola-jones is a method for detecting facial objects on images and CNN is a method for recognizing facial expressions. The viola-jones method has an average accuracy of 85.67% for detecting the location of faces and for CNN, the average accuracy for classifying emotions on faces is 52.46%.