Fingerprint Recognition using Fuzzy Logic with Triangular Pattern Template

A fingerprint is a pattern of ridges and valleys that exist on the surface of the finger. The uniqueness of a fingerprint is typically determined by the overall pattern of ridges and valleys as well as the local ridge structures e.g., a ridge bifurcation or a ridge ending, which are called minutiae points. Designing a reliable automatic fingerprint matching algorithm is quite challenging. However, the popularity of fingerprint sensors as they are becoming smaller and cheaper, automatic identification based on fingerprints is becoming not only attractive but an alternative complement to the traditional methods of identification. The critical factor in the widespread use of fingerprints identification is, satisfying the performance e.g., speed of matching and accuracy requirements of the application.  The widely used minutiae-based representation utilizes this discriminatory information available in a fingerprint for identification.  However, we propose a fingerprint recognition technique using fuzzy logic.  This approach utilizes two types of features; ridge ending and bifurcation to construct triangles and the fuzzy logic determine the degree of membership for matching.  The unique difference in our implementation is that fuzzy concept is used for matching rather than the feature extraction.  The laboratory results obtained indicate that matching process efficiency can be improved using this technique.