Emotion Recognition Through Facial Expressions: A Machine Learning Perspective in Mobile Multimedia

Facial expression-based emotion detection is very attractive because of the possibilities in security systems, mental health monitoring, and human-computer interaction. Even with the progress in accuracy in real-world settings, issues such as the lack of balanced datasets and the inability to differentiate between faint or superimposed emotions continue to plague it. This study aims to bridge these constraints by developing a CNN-based model that would be able to recognize face emotions reliably and be utilized in real-time situations, such as webcam integration. The Affect Net dataset, which is a comprehensive collection of over a million facial photos labeled with the seven major emotions of anger, disgust, fear, happiness, neutrality, sadness, and surprise, was used to train the proposed model. Other pre-processing data techniques used include grayscale conversion, normalization, scaling, and data supplementation to increase the robustness of the model. Using metrics like accuracy and loss trends for evaluation, the model demonstrated efficiency stability at around the 30th training phase. When the model is compared to existing models, this proposed model can attain the competitive level of accuracy up to approximately 60%. It also has the potential to run in real applications through its webcam integration. While the model can differentiate between various clear-cut emotions, it becomes ineffective at identifying subtle emotions, which include “Fear” and “Neutral” majorly because of unbalanced data and the subtleness of these expressions.