Extraction of segmented vein patterns using repeated line tracking algorithm

Abstract

Vascular biometrie is the method of analyzing the vein patterns or the patterns of blood vessels under the skin. The property of it being unforgeable, unspoofable, universal and unique, makes it highly preferable for a biometric authentication method. In this experiment, we have used CIE vein database, consisting of 1200 infrared palm images and 1200 infrared wrist images, each of 1280×960 resolution and of a 24-bit bitmap. In this paper, we have introduced a pre-processing phase followed by a feature extraction method. In the first stage, these images undergo several steps like; a) image acquisition, b) pre-processing, c) image normalization and d) post-processing. The binary image which is obtained in this phase is input for the next phase. Feature extraction of the vein patterns from the resulted binary image is based on line tracking algorithm with randomly start positions. Hence, the result has been recorded and found to be enhanced with this pre-processed technique.