Analysis of methods for finger vein recognition

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2013

Öğrenci: FARİBA YOUSEFİ

Danışman: SİNAN KALKAN

Özet:

A decade ago, it was observed that every person has unique finger-vein patterns and that this could be used for biometric identification. This observation has led to successful identification systems, which are currently used in banks, hospitals, state organizations, etc. For the feature extraction step of the finger-vein recognition, which is the most important step, popular methods such as Line Tracking (LT), Maximum Curvature (MC) and Wide Line Detector (WL) are used in the literature. Among these, the LT method is very slow in the feature extraction phase. Moreover, LT, MC and WL methods are susceptible to rotation, translation and noise. To overcome these drawbacks, this thesis proposes using some popular feature descriptors widely-used in Computer Vision or Pattern Recognition (CVPR) methods. The CVPR descriptors tested include, Fourier descriptors (FD), Zernike moments (ZM), Local Binary Patterns (LBP), Global Binary Patterns (GBP) and Histogram of Oriented Gradients (HOG) which have not been applied to the finger-vein recognition problem before. The thesis compares these descriptors against LT, MC and WL and analyze their running time, performance and resilience against rotation, translation and noise.