Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Analysis of Artificial Intelligence Based Human Expression
Ist Teil von
2023 4th International Conference on Smart Electronics and Communication (ICOSEC), 2023, p.1716-1719
Ort / Verlag
IEEE
Erscheinungsjahr
2023
Quelle
IEEE Xplore
Beschreibungen/Notizen
Facial Emotion Recognition (FER) is a current area of research in computer vision and machine learning. This study looks into how well Convolutional Neural Networks (CNNs) can identify face expressions of human emotion. CNNs have proven to perform exceptionally well in a range of computer vision applications, including image categorization, object recognition, and face recognition. To categorize the seven fundamental human emotions-anger, disgust, fear, happiness, sadness, surprise, neutral- a deep learning model is suggested utilizing CNNs. Convolutional and pooling layers are interspersed with fully connected layers for classification in the proposed model. The FER2013 dataset, which includes more than 35,000 photos, is the one utilized for training and evaluation. The performance of the proposed model was evaluated and compare it with the state-of-the-art approaches in terms of accuracy, precision, recall, and F1 score. The experimental findings show that the state-of-the-art performance in facial emotion recognition achieved by the proposed CNN-based model.