Occlusion-aware facial expression recognition: A deep learning approach

Facial expression recognition plays a crucial role in computer vision and human–computer interaction, with applications ranging from emotion analysis to social robotics. However, accurate recognition becomes challenging in the presence of occlusions, such as facial hair, glasses, and self-occlusion. This study addresses the problem of facial expression recognition despite occlusions and proposes a novel approach to overcome this challenge. The aim of this research is to develop a robust facial expression recognition framework that effectively handles occlusions and improves recognition accuracy. To achieve this, Hopfield networks, Deep Belief Networks (DBN), and Lanczos interpolation are integrated into the proposed method. Lanczos interpolation helps preserve image quality and reduces during resizing. The Hopfield network is utilized for feature extraction, capturing facial expression features even in the presence of occlusions. The DBN is employed for representation learning, fine-tuning the network using DenseNet to adapt to occluded facial expressions. To evaluate the proposed approach, extensive experiments were conducted on various datasets, including the Static Facial Expressions in the Wild (SFEW) dataset, AffectNet dataset, Real-world Affective Faces Database (RAF-DB), MMI Facial Expression Database, Oulu-CASIA NIR&VIS Facial Expression Database, and Extended Cohn-Kanade (CK +) dataset. The results demonstrate the superiority of our method in handling occlusions and achieving improved facial expression recognition accuracy compared to existing approaches. The contributions of this work are twofold: First, a novel framework is proposed that integrates Lanczos interpolation, Hopfield networks, DBN, and to effectively address the challenge of occlusions in facial expression recognition. Second, extensive experimental validation is provided on diverse datasets, highlighting the superior performance of our approach in handling occlusions and achieving accurate recognition. In conclusion, the proposed approach demonstrates its efficacy in improving facial expression recognition under occlusions. By effectively handling occlusions and capturing relevant features, our method opens up possibilities for enhanced emotion analysis, human–computer interaction, and social robotics applications.