e-journal
Thermal Imaging as a Biometrics Approach to Facial Signature Authentication
Abstract—A new thermal imaging framework with unique featureextractionandsimilaritymeasurementsforfacerecognitionis presented.Theresearchpremiseistodesignspecializedalgorithms thatwouldextractvasculatureinformation,createathermalfacial signature, and identify the individual. The proposed algorithm is fullyintegratedandconsolidatesthecriticalstepsoffeatureextractionthroughtheuseofmorphologicaloperators,registrationusing theLinearImageRegistrationTool,andmatchingthroughunique similarity measures designed for this task. The novel approach at developing a thermal signature template using four images taken at various instants of time ensured that unforeseen changes in the vasculature over time did not affect the biometric matching processastheauthenticationprocessreliedonlyonconsistentthermal features.Thirteensubjectswereusedfortestingthedevelopedtechniqueonanin-housethermalimagingsystem.Thematchingusing thesimilaritymeasuresshowedanaverageaccuracyof88.46%for skeletonized signatures and 90.39% for anisotropically diffused signatures. The highly accurate results obtained in the matching process clearly demonstrate the ability of the thermal infrared system to extend in application to other thermal-imaging-based systems. Empirical results applying this approach to an existing database of thermal images prove this assertion.
Index Terms—Biometric, face recognition, image registration, image segmentation, thermal imaging.
Tidak ada salinan data
Tidak tersedia versi lain