| 基于各向异性逆扩散方程的指纹图像锐化去噪方法 |
| |
| 引用本文： | 郝玉峰,袁春伟.基于各向异性逆扩散方程的指纹图像锐化去噪方法[J].数据采集与处理,2005,20(3):258-262. |
| |
| 作者姓名： | 郝玉峰 袁春伟 |
| |
| 作者单位： | 东南大学,生物医学工程系,南京,210096 |
| |
| 基金项目： | 国家自然科学基金（69831010）资助项目. |
| |
| 摘 要： | 基于逆扩散过程的启发,提出各向异性逆扩散算法用于指纹图像的锐化去噪方法,克服了退化扩散方程对大曲率边缘点的模糊效应,兼顾了去噪和保持边界这一矛盾的两个方面,尤其适合于纹理密集的指纹图像锐化.实验结果表明,本文算法对于带噪指纹图像的锐化效果明显优于以往非线性扩散处理算法.
|
| 关 键 词： | 图像增强 偏微分方程 各向异性扩散 指纹 |
| 文章编号： | 1004-9037（2005）03-0258-05 |
| 收稿时间： | 2004-04-28 |
| 修稿时间： | 2005-05-31 |
Fingerprint Image Sharpening and Denoising Method Based on Nonlinear Anisotropic Reverse Diffusion Equation |
| |
| HAO Yu-feng,YUAN Chun-wei.Fingerprint Image Sharpening and Denoising Method Based on Nonlinear Anisotropic Reverse Diffusion Equation[J].Journal of Data Acquisition & Processing,2005,20(3):258-262. |
| |
| Authors: | HAO Yu-feng YUAN Chun-wei |
| |
| Abstract: | Considering the feature of the fingerprint, a nonlinear anisotropic reverse diffusion algorithm is proposed from the reverse diffusion phenomena in physics. The method is effective for both noise removing and edge preserving, mainly because it prevents the blurring effect on the degenerate diffusion equation for the points with big gray level variations. Compared with nonlinear diffusion methods, the algorithm has better performances for preprocessing noisy fingerprint images. |
| |
| Keywords: | image enhancement PDE anisotropic diffusion fingerprint |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
