Face recognition technology has been widely adopted in many mission-critical applications as a means of human identification, controlled admission, E-bank authentication, and mobile device access. Security surveillance is also a growing application for face recognition techniques; however, challenges exist from low resolution (LR) and high noise, multi-angle and multi-distance changes, and different light conditions. In comparison, algorithms applied to cell phone imagery or other specific camera devices mainly function on high resolution images with fixed angles and small changes of illumination. As face recognition in security surveillance becomes more important in the era of dense urbanization, it is essential to develop algorithms that are able to provide satisfactory performance in processing the video frames generated by low resolution surveillance cameras. In this paper, we propose a novel face recognition method that is suitable for low resolution surveillance cameras. The technique is demonstrated on a face dataset generated from real-world surveillance scenarios, from which an end-to-end approach is taken to match high resolution (HR) images with low resolution (LR) images from the surveillance video. The experimental results validate the effectiveness of the novel method that improves the accuracy of face recognition in surveillance security scenarios.