Palm Vein Recognition using Local Tetra Patterns

Palm Vein Recognition is an emerging touch-less and spoof-resistant means of biometric authentication. However, matching algorithms tend to lack accuracy, due to the complexity of vascular patterns and irregularities in subsequent samples of the same person. This paper proposes a method that describes the spatial structure of local texture using direction of central gray pixel, formulating a discrete set of features which generates a unique template that improves the accuracy of identification. The features from various samples pertaining to the same person are strategically combined. This creates a robust feature vector which is able to handle the irregularities encountered while acquiring images for the database, and improves the efficiency manifolds as compared to present techniques. Matching and score calculation was done using cosine similarity measure. The method was tested on the PUT Vein Database which contained 1200 samples. The results showed an Equal Error Rate of 0%.