Finger Vein Recognition Method Based on Gaussian Low-Pass Filter and Direction Detection
Lin Xuan You, Lei Sun, Fenghai Li, Xueshuang Li · 2014
The recognition results of some finger vein recognition algorithms are greatly affected by the quality of the finger vein images. To overcome this effect in some extend, a new finger vein image recognition method is presented based on both the Gaussian low-pass filter and the direction detection. In order to keep the finger vein structure completely, a modulated Gaussian low-pass filter is used to smooth and enhance the images. Considering the valley-shaped feature of the finger vein, a new group of oriented operators are designed to detect the directions of a finger vein image and calculate every pixel's directional value accurately. And then, the Niblack method is used to segment the enhanced image and the skeleton feature is extracted from the finger vein pattern for recognition. Finally, we use the modified Hausdorff distance method to achieve the recognition of the finger vein images. Experimental results show that the proposed algorithm is of higher finger vein extraction accuracy and lower Equal Error Rate (EER).