A novel online fingerprint segmentation method based on frame-difference

Fingerprint image segmentation is an important step in an automatic fingerprint identification system (AFIS). A successful segmentation can remove the background in the fingerprint image so as to reduce the performance time of the image enhancement and the number of false features. The conventional methods segment fingerprints by using information of orientation or grey deviation; however, there are some difficulties in dealing with remaining fingerprint and spots. In this paper, we present a novel online fingerprint segmentation method based on frame difference. In our method, the segmentation is performed in the online process of capturing image, not using information of orientation or grey deviation. The background is extracted from the sequential images captured by fingerprint sensor and the background is removed by using frames difference. The background with the remaining fingerprints and spots can be removed effectively by the method. The approach has been used in the fingerprint identification system. The performance of the system and the experimental results prove its practicability and efficiency.