Palm Vein Preprocessing Image based on Homomorphic Filtering
Mona A. Ahmed, Hala M. Ebied, El-Sayed M. El-Horbaty, Abdel-Badeeh Mohamed Salem · 2014
In this paper we propose an image analysis method to extract region of interest (ROI) from palm vein image. After extracting ROI we design a sequence of preprocessing steps to remove the translation and rotation of palm vein images introduced in the data collection process and reduce a lot of data amount without losing much useful information. Then design a sequence of preprocessing steps that enhances the contrast between palm vein patterns and background using Homomorphic filter and Canny filter. The experimental results demonstrate that the recognition rate of our algorithm reaches 99.3% on CASIA Multi-Spectral Palmprint Image Database V1.0 (CASIA database).