手掌静脉图像增强算法研究

Research of Enhanecd Algorithm of Palm Vein Image

为了解决手掌静脉图像质量局部不均问题,提出一种新的手掌静脉增强算法,将受约束的局部直方图均衡算法(CLAHE)和非下采样的Contourlet变换(NSCT)相结合进行图像增强.对图像进行非下采样Contourlet变换,在近似分量上进行CLAHE处理提高图像对比度,在细节分量上根据各尺度不同方向子带上的能量分布自适应地确定阈值,并利用所提出的非线性增强算法进行细节增强;然后通过Gabor滤波器增强手掌静脉纹路.实验表明,该算法提高了静脉图像对比度,增强了手掌静脉的轮廓细节,并且有效地抑制了噪声.

This paper presents a new methods that enhance the image of palm vein based on Contrast Limited Local Histogram Equalization （CLAHE） and Nonsubsampled Contourlet Transform （NSCT） to overcome the influence of the uneven quality of local area. After making NSCT in the original image, CHLHE is used to enhance image contrast in the approximate coefficient, and in the detail cofficient, the threshold is determined adaptively according to the energy distribution of the different scale sub-pass directions, the details are enhanced by means of the non-linear enhancement algorithm. At last, the lines of the palm vein are enhanced by Gabor filter. The experiments show that this algorithm can improve the contrast of the vain images and the details of the outlines, and in addition it can effectively reduce the noise.