Blur and Illumination Robust Face Recognition and Facial Expressions

Facial expression is the natural means for human beings to show their emotions and motivations. The problem of unconstrained face recognition from remotely acquired images is addressed. When blurring comes to picture, face recognition becomes difficult. The main factors that make this problem challenging are image degradation due to blur and the appearance variations due to illumination and pose. Many of the approaches concentrate mainly on the blurring part alone. A blur-robust face recognition algorithm DRBF (Direct Recognition of Blurred Faces) and IRBF (Illumination-Robust Recognition of Blurred Faces) is proposed in this paper. This algorithm can easily incorporate prior knowledge on the type of blur as constraints. In addition to this, the illumination defects are also considered along with the blur problems. And the features of facial components such as eyes, nose, and mouth in gray images of faces are extracted and the facial expressions are identified.