DESIGN AND IMPLEMENTATION OF A NIGERIAN FACIAL EMOTION RECOGNITION APPLICATION

This project presents the development of a Nigerian Facial Emotion Recognition Application using Convolutional Neural Networks (CNN) and deep learning techniques. The primary objective is to accurately detect and classify facial emotions specific to Nigerian facial features and expressions. By leveraging a deep learning approach, the system is trained on a dataset containing diverse facial images representing various emotions. The MobileNet model was fine-tuned for this task. The CNN architecture is employed to extract features from these images, enabling the model to learn the subtle variations in expressions. The model undergoes extensive training and testing to ensure high accuracy and robustness in real-world scenarios. The FER model’s performance was evaluated based on its performance on a customized dataset containing faces of Nigerians. The model attained an accuracy of 98.6% training accuracy and 98.0% validation accuracy. The results demonstrate the effectiveness of deep learning in recognizing complex facial emotions, providing a reliable tool for applications in psychology, security, and human-computer interaction in Nigeria.