基于改进阈值函数的手指静脉图像增强算法

Finger vein image enhancement algorithm based on improved threshold function

针对传统图像增强算法对含噪手指静脉图像增强效果差、易丢失图像细节信息的问题,提出一种基于改进阈值函数的手指静脉图像增强算法。首先,对手指静脉图像进行二维小波变换,将小波变换后的低频子带系数非线性增强,各高频子带系数脊波变换得到脊波系数。然后,在脊波域利用改进阈值函数对脊波系数进行处理,将改进后的脊波系数通过脊波逆变换到小波域。最后,在小波域进行小波图像重构,得到增强后的手指静脉图像。实验结果表明,该算法在频域上能够有效降低噪声,减少失真并保留了较高的信息量,有较好的图像增强效果。

Aiming at the problem that traditional image enhancement algorithms have poor enhancement effect on noisy finger vein images and are easy to lose image detail information,a finger vein image enhancement algorithm based on improved threshold function is proposed.Firstly,two-dimensional wavelet transform is applied to finger vein images,the low frequency sub-band coefficients are processed by using the nonlinear enhancement,the ridgelet coefficients are obtained by the ridgelet transform of the high frequency sub-band coefficients.Then,the improved threshold function is used to process the ridgelet coefficients in the ridgelet domain,and the improved ridgelet coefficients are transformed into wavelet domain through the inverse ridgelet transform.Finally,the enhanced finger vein image is obtained by wavelet reconstruction in wavelet domain.Experimental result shows that the proposed algorithm can effectively decrease noises in the frequency domain,and retain a higher amount of information and reduce distortion.It has better effects in image enhancement.