Implementasi Metode Convolutional Neural Network (CNN) Pada Sistem Deteksi Emosi dari Ekspresi Wajah Manusia dengan Aplikasi Android sebagai Antarmuka Pengguna

Emotion detection through human facial expressions plays an important role in various fields, such as human-computer interaction, psychology, and artificial intelligence. This thesis describes the implementation of Convolutional Neural Network (CNN) for emotion detection system based on human facial expressions, with an Android application as the user interface. The dataset used to train the CNN model consists of fer2013 and muxspace, which includes thousands of human facial images with various expressions. The system development includes data preprocessing, CNN model training, model evaluation and optimization, and integration with the Android application. The results show that the generated model is capable of accurately identifying emotions from human facial expressions in realtime and can be used in various practical applications.