Abstract: Aiming at the illumination and blurring problems that affect the accuracy of face recognition in the use of railway face recognition gates, this paper proposed a face illumination adaptive adjustment algorithm to improve the accuracy of face recognition under non ideal lighting conditions, designed a clear fuzzy identification algorithm for face images to select clear face images and improve the accuracy of face recognition in passenger moving scenes. The algorithm experiments were carried out in self-built data sets. Experimental results show that the accuracy rate of face recognition reaches 97.21% using the algorithm designed in this paper, which can meet the needs of practical applications and has the value of popularization..