自适应阈值小波在指纹图像去噪中的应用  

Application of Adaptive Threshold Wavelet in Fingerprint Image Denoising

作　　者：林玉娥[1] 孙然然 梁兴柱[1,2] 苏树智 LIN Yue;SUN Ranran;LIANG Xingzhu;SU Shuzhi(School of Computer Science and Engineering,Anhui University of Science and Technology,Huainan Anhui 232001,China;Institute of Environment-friendly Materials and Occupational Health (Wuhu),Anhui University of Science and Technology, Wuhu Anhui 241003, China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001 [2]安徽理工大学环境友好材料与职业健康研究院(芜湖),安徽芜湖241003

出　　处：《安徽理工大学学报（自然科学版）》2021年第6期32-38,共7页Journal of Anhui University of Science and Technology:Natural Science

基　　金：国家自然科学基金资助项目(61806006);安徽省教育厅自然科学基金资助项目(KJ2018A0084);芜湖市科技计划基金资助项目(2020yf48)。

摘　　要：目前指纹识别技术具有很广泛的应用,但通常指纹图像含有混合噪声,而传统小波阈值去噪算法对含有混合噪声的图像去噪时,存在混合噪声去除不彻底的问题,为此提出了一种改进的自适应阈值和连续型低误差阈值函数的小波去噪算法。首先,算法对含有混合噪声的指纹图像进行一次中值滤波去噪。然后,设计了一种新的自适应阈值,小波分解层数越大新阈值就会越小,就能更好地体现噪声信号在进行小波分解时减小的特征。最后,设计了连续型低误差改进阈值函数,改进的函数是连续的,并且阈值达到极限时误差为0。改进后的算法使得估计的小波系数更加接近真实系数,重构后的图像更接近原始图像。实验结果表明,该算法对含有高斯噪声和椒盐噪声的指纹图像处理时,相比于其他算法,得到了更好的峰值信噪比和均方误差数值,去噪后的指纹图像纹理显示更加清晰。At present,fingerprint identification technology is widely used,but usually fingerprint images contain mixed noise and the traditional wavelet threshold denoising algorithm has the problem of incomplete removal of mixed noise on image denoise.Therefore,an improved wavelet denoising algorithm with adaptive threshold and continuous low error threshold function is proposed.Firstly,the algorithm denoises the fingerprint image with mixed noise by median filtering.Then,a new adaptive threshold is designed.The larger the number of wavelet decomposition layers,the smaller the new threshold,which can better reflect the characteristics of noise signal reduction during wavelet decomposition.Finally,a continuous low error improved threshold function is designed.The improved function is continuous,and the error is 0 when the threshold reaches the limit.The improved algorithm makes the estimated wavelet coefficients closer to the real coefficients and the reconstructed image closer to the original image.The experimental results show that compared with other algorithms,the algorithm obtains better peak signal-to-noise ratio and mean square error,and the texture of the denoised fingerprint image is clearer.

关 键 词：小波阈值 图像去噪 中值滤波 自适应阈值 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]