摘要
为了确保指纹特征提取算法的鲁棒性,需要对原始指纹图像进行预处理以增强纹线的清晰度,增加脊线和谷线的对比度,减少伪信息.实现了一种基于Curvelet变换的指纹图像增强算法,阐述了Curvelet变换的定义及其应用于指纹图像增强的过程,研究了Curvelet系数的调整方法.Curvelet变换比小波变换能够更好的描绘图像的边缘,而且具有很强的方向性.实验证明,应用Curvelet变换能够较好的解决指纹图像的增强问题.
In order to ensure the robustness of the minutiae extraction algorithm from the input fingerprint images, it is essential to preprocess the original fingerprint images to enhance the ridge clarity and the contrast of the ridge and valley, and reduce spurious ridge information. A fingerprint image enhancement algorithm is presented based on the curvelet transform in this paper. The curvelet transform is defined and its application process in the fingerprint enhancement are described. The coefficients adjustment method is proposed. The curvelet transform mpresents edges better than wavelet transform, and has good directivity. Experimental results show that the fingerprint image can be enhanced by curvelet transform.
出处
《山东大学学报(工学版)》
CAS
2005年第6期55-58,107,共5页
Journal of Shandong University(Engineering Science)