Article Preview
Top1. Introduction
Over the past ten years, face recognition (FR) has received substantial attention from researchers in biometrics, pattern recognition, computer vision, and cognitive psychology communities (Hsu, 2002). FR is a difficult problem due to the general similar shape of faces combined with the numerous variations between images of the same face. Recognition of faces from an uncontrolled environment is a very complex task: lighting condition may vary tremendously; facial expressions also vary from time to time; face may appear at different orientations and a face can be partially occluded. Further, depending on the application, handling facial features over time (aging) may also be required. Although existing methods perform well under constrained conditions, the problems with the illumination changes, out of plane rotations and occlusions still remain unsolved. The area of face recognition is well described at present, e.g. starting by conventional approaches (PCA, LDA) (Turk & Pentland, 1991; Marcialis & Roli, 2002; Martinez & Kak, 2001), and continuing at present by kernel methods (Wang, et al., 2008; Hotta, 2008; Wang et al., 2004; Yang, 2002; Yang et al., 2005). Advances in face recognition are summarized also in books (Li & Jain, 2005; Delac et al., 2008) and book chapters (Oravec et al., 2008).
Environmental corruption such as noise, blur, adverse illumination and compression rates (in JPEG and other compression techniques) influence the performance of state-of-art recognition algorithms. Several enhancement methods have been proposed in literature to handle these corruptions (Chang, 2000). Using denoising techniques to enhance the quality of images will increase both complexity and computational cost besides that its performance depends on the type and quantity of noise. So, this paper aims to enhance the performance of recognition systems in noisy environment in simple manner without using denoising techniques. This is done by using a combination of GF with PCA for efficient feature extraction, and ANN that are trained in a special method for classification.