一种手背静脉感兴趣区域提取算法

When collecting the back-of-hand vein images, due to reasons such as rotation and translation of the back of the hand, deviations may occur when collecting the effective recognition area, causing interference to recognition. In order to quickly locate the effective recognition area, according to the characteristics of the collected images, a region-of-interest extraction algorithm based on the maximum inscribed circle is proposed. For the collected back-of-hand vein images, the center of the maximum inscribed circle and the centroid are calculated, and the rotation angle of the back of the hand is calculated using the center of the inscribed circle and the centroid. The position of the back-of-hand vein image is corrected according to the rotation angle, and the region of interest for recognition is extracted. This algorithm is based on the contour of the back of the hand and is not affected by human factors, and can eliminate the effects of translation and rotation. The experimental results show that this method has good robustness.

在手背静脉图像采集时由于手背旋转和平移等原因,会造成采集有效识别区域时出现偏差,给识别带来干扰,为实现快速定位有效识别区域,依据采集图像的特点,提出了一种基于最大内切圆的感兴趣区域提取算法。针对采集的手背静脉图像,计算最大内切圆心与质心,并利用内切圆心与质心计算手背的旋转角度,根据旋转角度矫正手背静脉图像位置,提取感兴趣识别区域。该算法基于手背轮廓,不受人为因素的干扰,可以消除平移和旋转的影响。实验结果表明该方法具有很好的鲁棒性。