Impact of Deep Learning Approaches on Facial Expression Recognition in Healthcare Industries

Facial expression recognition system can provide quick assistance to the healthcare system and exceptional services to the patients. A facial expression recognition system has been proposed in this work. The implementation of the proposed approach has been divided into three components. In the first component, landmark points on the facial region has been detected. The detected face region is normalized to its fixed size and then down-sampled to its varying sizes producing multi-resolution images. Different CNN architectures have been proposed in the second component to analyze the texture patterns in the multi-resolution facial images. Data augmentation, progressive image resizing, transfer-learning, and fine-tune of parameters have been employed in the third component to extract more distinctive & discriminant features and enhance the proposed CNN models' performance. Extensive experimentation has been carried out using Karolinska directed emotional faces (KDEF), Cohn-Kanade (CK+), and Static Facial Expressions in the Wild (SFEW) benchmark databases and the performance have been compared with some existing methods concerning these databases. The comparison shows that the proposed facial expression recognition system outperforms other competing methods.