Procedia Computer Science · 2016 · 12 citations · 12 references
ComputingCybersecurityAuthenticationBiomedical ImagingDigital ForensicsBiometric AuthenticationForensic EvidenceBiometric Feature ExtractionBiometric RecognitionContrast-limited Adaptive Histogram EqualizationFalse Acceptance RateFalse Rejection RateFinger Vein RecognitionHistogram EqualizationLocal Binary Patterns
This paper proposes a novel authentication system using hidden biometric trait called finger vein (FV). Proposed finger vein acquisition device captures the superficial vein pattern present under the skin of finger. The vein pattern of all fingers of human being is not same. Each finger of same person has different vein pattern. It is the hidden part which is not seen by normal eye sight hence less possible to forge. The paper highlight the primary set up of NIR based finger vein acquisition device to capture the superficial vein pattern that shows the unique features require for recognition. This Paper explores the bilateral and contrast limited histogram equalization technique to enhance finger vein raw samples captured by proposed finger vein acquisition. The performance is verified using Local Binary Pattern (LBP) algorithm. The recognition accuracy is represented by graph between True Acceptance Rate (TAR) vs. True Rejection Rate (TRR). It is observed that TAR Vs TRR for standard data base is 94. 5% and for own data base is 94.34%. It shows that FV has potential for personal identification.
12
Bilateral filtering for gray and color images
Carlo Tomasi, Roberto Manduchi · 2002 · 8.1K citations
Arts, Vision Science, Color Vision +16
Adaptive histogram equalization and its variations
Stephen M. Pizer, E. Philip Amburn, John D. Austin et al. · Computer Vision Graphics and Image Processing · 1987 · 3.9K citations