Today, with widespread and increasing need for community safety in critical facilities and public organizations, Methods for identification and verification of peoples become a key technology in these places. Such a need for reliable identification resulted in increasing attention to biometric technology. Since the most common method for identifying individuals is their faces, Face can be considered as one of the most accepted biometric criteria. The face recognition can be considered one of the threads of research over the past 20 years which attracted many researchers in various fields of science such as psychological science and computer science. Many face recognition systems have reached the desired level of performance but developing a face recognition system with good performance in uncontrolled conditions still remains a scientific challenge. In such environments, noise and lack of high resolution images caused a severe drop in performance. In this thesis we tried to develop a new face recognition system based on fusion of local descriptors. To this end, two new local descriptors are introduced and thoroughly examined. Then fusions of these descriptors in two forms are evaluated. To reduce the high dimensional feature space, resulting feature spaces are projected on LDA sub-space corresponding to different areas of face image to produce a discriminative face representation and robust to noise and low resolution face images. Also for reducing the effects of poor lighting condition on face recognition performance, we have introduced a new pre-processing method for illumination normalization of face images. In this method, poor illuminated face images are adjusted using dynamic range compression. Afterward contrast of resulting image from previous step are improved to have a good visually adjusted face image. For evaluation of introduced face recognition system, ORL and Yale datasets and for evaluation of illumination normalization method Yale B dataset are used. The results obtained in experiments show that introduced face recognition system has ability to recognize faces under severe noisy condition and low resolution images and can achieve good performance with few training images. Keywords: Face Recognition, Local Discriptors, Linear Discriminant Sub-space, Illumination Normalization