6533b7d1fe1ef96bd125cd2b

RESEARCH PRODUCT

Morphological Enhancement and Triangular Matching for Fingerprint Recognition

Filippo SorbelloG. MiliciSalvatore VitabileVincenzo Conti

subject

ScannerMatching (graph theory)business.industryComputer scienceFingerprint (computing)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFingerprint Verification CompetitionPattern recognitionFingerprint recognitionAutomated Fingerprint Identification System (AFIS)Tree (data structure)Computer Science::Computer Vision and Pattern RecognitionArtificial intelligenceAutomated fingerprint identificationbusinessRotation (mathematics)ComputingMethodologies_COMPUTERGRAPHICSComputer Science::Cryptography and Security

description

Among the principal problems for realizing a robust Automated Fingerprint Identification System (AFIS) there are the images quality and matching algorithms. In this paper a fingerprint enhancement algorithm based on morphological filter and a triangular matching are introduced. The enhancement phase is based on tree steps: directional decomposition, morphological filter and composition. For the matching phase a global transformation to overcame the effects of rotation, displacement and deformation between acquired and stored fingerprint is performed using the number of similar triangular, having fingerprint minutiae as vertexes. The performance of the proposed approach has been evaluated on two set of images: the first one is DB3 database from Fingerprint Verification Competition (FVC) and the second one is self collected using an optical scanner.

yearjournalcountryeditionlanguage
2008-08-14
http://hdl.handle.net/10447/14714