This paper presents a multi-finger knuckle recognition system and proposes a finger knuckle region extraction algorithm from a video sequence. The use of video sequences makes it possible to achieve stable and robust finger knuckle region extraction, since the optimal image frame can be selected from a set of image frames to extract a region to be matched for each finger. Through a set of experiments, we demonstrate that the extraction rates of the proposed algorithm are 96.4%, 99.4%, 97.6% and 96.4% for index, middle, ring and little fingers, respectively, which are acceptable in practice. The result indicates that four fingers can be used for person authentication in most cases. We also demonstrate that the use of multiple finger knuckle regions exhibits efficient performance for person authentication.