Analysis on Performance of Facial Expression Recognition using Conventional and Deep Learning Approaches

The ability to identify a person's inner thoughts through expressions before verbalizing is known as Facial Expression Recognition (FER). Nowadays, the phrase “Human-Computer Interaction” has become the most frequently searched keyword, especially in research on automatic depression diagnosis, psychiatric illness, false narratives, and suppressed emotions. The main objective of this survey is to give a clear view of automatic FER models. Also, this research work highlights the different problems encountered in the determination of facial characteristics. For better knowledge, first various emotion databases are listed with the range of emotions that each database has recognized. Further, this paper has been organized in such a way to provide a thorough and better discussion on the three phases of the facial expression recognition model. Then, various approaches are compared and adopted in image-based and video-based FER models from recent findings and finally, this research study has provided the right directions on how robust and challenging models for future research can be developed.