Fast Vein Pattern Extraction Based on a Binary Filter

摘要

Vein pattern extraction from Near-infrared (N1R) images is essential in most vein recognition algorithms. Among many vein recognition systems, the matched filter has been widely applied because it works well in enhancing vein images. However, the matched filter is time-consuming as it uses multi-scale and multi-orientation Gauss or Gabor filters to generate the Matched Filter Response (MFR) images. In this paper, we propose a binary filter for vein pattern extraction which can achieve similar results as the Gauss or Gabor filter but with fewer parameters and faster processing speed. The proposed method could process 27 images with image resolution of 320 * 240 per second, which is about three times faster than Gauss or Gabor filter.