Vein Feature Extraction Using DT-CNNs
Suleyman Malki, Yu Fuqiang, Lambert Spaanenburg · 2006
Biometric identification is an important security application that requires non-intrusive capture and real-time processing. Security systems based on fingerprints and retina patterns have been widely developed, but can be easily falsified. Recently, identification by vein patterns has been suggested as a promising alternative. In this paper an existing feature extraction algorithm, that has been developed for fingerprint recognition, is adapted for vein recognition. The algorithm has been implemented as cellular neural network and realized on a field-programmable gate-array. The detection quality is comparable to the 99.45% reached earlier by direct image comparison, but suffers from the image resolution sensitivity of the false feature elimination