Here we proposed a fingerprint classifierframework. A combination scheme involvingdifferent fingerprint classifiers whichintegrates vital information is likely toimprove the overall system performance.The fingerprint classifier combination can beimplemented at two levels feature level anddecision level. We use the decision levelcombination that is more appropriate whenthe component classifiers use different typesof features. Kittler provides a theoreticalframework to combine various classifiers atthe decision level. Many practicalapplications of combining multiple classifiershave been developed. Brunelli and Falavignapresented a person identification system bycombining outputs from classifiers based onAudio and visual.Here the combination approach is designed atthe decision level utilizing all the availableinformation, i.e. a subset of (Fingerprint)labels along with a confidence value, calledthe matching score provided by each of thenine finger print recognition method.
Classification of Fingerprint(Level-1,Level -2 & Level-3) Features
Level 1 features describe the ridgeflow pattern of a fingerprint. According tothe Henry classification system there areeight major pattern classes, comprised of whorl, left loop, right loop, twin loop, arch,tented arch. as shown in the figure 1.,
Fig 1. Fingerprint Level 1 Features
Level 2 features describe various ridgepath deviations where single or multipleridges form abrupt stops, splits, spursbifurcation Composite minutiae (i.e., forks,spurs, bridges, crossovers and bifur-cations)can all be considered as combinations of these basic forms enclosures, etc. Thesefeatures, known as the Galton points orminutiae, have two basic forms: ridge endingand ridge as shown in fig 2.
Fig 2. Fingerprint Level 2 Features
Level 3 features refer to alldimensional attributes of a ridge, such asridge path deviation, width, shape, pores,edge contour, incipient ridges, breaks,creases, scars and other permanent details asshown in fig 3.
(IJCSIS) International Journal of Computer Science and Information Security,Vol. 8, No. 7, October 2010129http://sites.google.com/site/ijcsis/ISSN 1947-5500