IN DEPTH ANALYSIS OF PREPROCESSING, MINUTIAE EXTRACTION AND POST PROCESSING IN FINGERPRINT SYSTEM

Conventional algorithms for fingerprint recognition are mainly based on minutiae information. However, the small number of minutiae in partial fingerprints is still a challenge in fingerprint matching. In fingerprint recognition systems, there are frequently appeared partial fingerprints, such as incompletely touching in fingerprint scanning or latent fingerprints. In this paper, we studied the influence of the fingerprint area in partial fingerprint recognition. First, a simulation scheme was proposed to construct a serial of partial fingerprints with different area. Then, the influence of the fingerprint area in partial fingerprint recognition is studied. By comparing the performance of partial fingerprint recognition with different fingerprint area, some useful conclusions can be drawn: (1) The decrease of the fingerprint area degrades the performance of partial fingerprint recognition; (2) When the fingerprint area decreases, the genuine matching scores will decrease, whereas the im-poster matching scores will increase; (3) When the area of partial fingerprints is smaller than 20,000 pixels (about fifth of the normal full fingerprints), the performance of partial fingerprint recognition becomes very poor; (4) The threshold value of a given false accept rate increases when the area of partial fingerprints decrease a lot, but it remains almost the same if the area of partial fingerprints decrease not so much, e.g., greater than 50,000 pixels (about half of the normal full fingerprint). These observations can be helpful in improving the performance of partial fingerprint recognition in the future.