Similar classification performance was obtained on the NIST-9 database. Using a reject option, the four-class classification error can be reduced to less than 6% with 10% fingerprint images rejected. For he NIST-4 database, classification accuracies of 85.4% for the five-class problem and 91.1% for the four-class problem (with arch and tented arch placed in the same category) were achieved. The classifier was tested on 4000 images in the NIST-4 database and on 5400 images in the NIST-9 database. A fingerprint pattern which possesses either an angle, an upthrust, or two of the three basic characteristics of a loop. The classifier is rule-based, where the rules are generated independent of a given data set. Arches have a moundlike contour, while tented arches have a spikelike or. There are a number of uses for tented arch fingerprints. The plain arch requires no further description, the tented arch is so called. This results in a raised area in the center of the arch. The main feature of arches is the absence of deltas, and consequently of. The classifier is invariant to rotation, translation and small amounts of scale changes. fingerprint, impression made by the papillary ridges on the ends of the fingers. The tented arch is believed to be caused by a fusion of the lower parts of the ridges that form the arches in the fingerprint.
The algorithm extracts singular points (cores and deltas) in a fingerprint image and performs classification based on the number and locations of the detected singular points. Fingerprints are classified into five categories: arch, tented arch, left loop, right loop and whorl. A fingerprint classification algorithm is presented in this paper.
0 kommentar(er)
