6533b7d6fe1ef96bd1265d1b

RESEARCH PRODUCT

A Novel Iris Recognition System based on Micro-Features

Filippo SorbelloG. MiliciSalvatore VitabileVincenzo Conti

subject

MinutiaeMatching (graph theory)Biometricsbusiness.industryIris recognitionFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPattern recognitionFingerprint recognitionComputingMethodologies_PATTERNRECOGNITIONGeographyiris micro-characteristIcs recognition systemPreprocessorComputer visionIRIS (biosensor)Artificial intelligencebusiness

description

In this paper a novel approach for iris recognition system based on iris micro-features is proposed. The proposed system follows the minutiae based approach developed for fingerprint recognition systems. The proposed system uses four iris microfeatures, considered as minutiae, for identification. The individualized characteristics are nucleus, collarette, valleys and radius. Iris recognition is divided in three main phases: image preprocessing, micro-features extraction and matching. The algorithm has been tested on CASIA v1.0 iris image database obtaining an high accuracy. The obtained experimental results have been analyzed and compared with the Daugman based approach.

yearjournalcountryeditionlanguage
2007-06-01
http://hdl.handle.net/10447/29922