Facial Expression Analysis and Estimation Based on Facial Salient Points and Action Unit (AUs)

Humans use their facial expressions as one of the most effective, quick, and natural ways to convey feelings intentions others. In this research, presents analyses human structure along with its components using Facial Action Units (AUs) Geometric structures for identifying expressions. The approach considers such Nose, Mouth, eyes eye brows FER. Nostril contours left lower tip, right centre tip are considered salient points Nose. Various Mouth extracted from end point, upper lip mid curve. These all expression same subject considering neutral face reference. is mapped other faces. deformation estimated Euclidean distance. classification algorithms LibSVM, MLP, RF has achieved accuracy 86.56% on an average. findings experiments show that extraction picture characteristics more efficient in terms computing gives promising outcomes.