Abstract: The Systems that rely on Face Recognition (FR) biometric have acquired great importance ever since terrorist threats injected weakness among the implemented security systems. Rest biometrics as iris or Fingerprints recognition is not trustworthy in such situations whereas FR is considered as a better compromise. In Image processing, Occlusion refers to facade of the face image which can be due to hair, moustache, sunglasses, or wrapping of facial image by scarf or other accessories. Efforts on FR appears in controlled environment have been in the picture for past several years; however identification under uncontrolled condition like partial occlusion is typically quite a matter of concern. Based on review of literature and its analysis so far, a classification made in this paper to solve the challenges in recognition of face in the presence of partial occlusion. The methods used are INPAINTING based methods that make use of Exemplar-based Inpainting, Feature-Extraction, and Fast Weighted-Principal component analysis (FW-PCA),etc. The presented approach in this paper describes the removal of Occlusion from images or restore the occluded part of image using Exemplar-based Image Inpainting technique, feature extraction and FW-PCA(Restoration) combinations.
Keywords: Occlusion; Image Inpainting; Exemplar based inpainting technique, Face-detection, Feature extraction, Image Restoration, FW-PCA