| 图像修复的CDD模型新算法 |
| |
| 引用本文： | 王军锋,裴艳侠,王涛. 图像修复的CDD模型新算法[J]. 计算机系统应用, 2016, 25(8): 135-138 |
| |
| 作者姓名： | 王军锋 裴艳侠 王涛 |
| |
| 作者单位： | 西安理工大学 理学院, 西安 710054,西安理工大学 理学院, 西安 710054,西安理工大学 理学院, 西安 710054 |
| |
| 基金项目： | 陕西省自然科学基金（2015JQ1022） |
| |
| 摘 要： | CDD图像修复模型是在TV模型的基础上引入曲率项来满足视觉的“连接性”原则. 考虑到该模型各参考点梯度模值大小的不同及扩散效率的不足，本文结合退化扩散模型提出了一种新的CDD模型图像修复算法. 该算法利用待修复区域像素点的梯度和等照度线的曲率信息来控制各参考点对破损区域的贡献值，并进一步作加权处理. 最后将该模型的偏微分方程离散化，给出了模型的数值实现方法. 实验结果表明该算法能保证图像边缘的视觉连通性，并在相同迭代次数的情况下，修复效果明显优于CDD算法，是一种有效的新方法.
|
| 关 键 词： | 图像修复 退化扩散 CDD算法 梯度 各向异性 |
| 收稿时间： | 2015-12-07 |
| 修稿时间： | 2016-01-14 |
New Algorithm of Image Inpainting Curvature-Driven Diffusion Model |
| |
| WANG Jun-Feng,PEI Yan-Xia and WANG Tao. New Algorithm of Image Inpainting Curvature-Driven Diffusion Model[J]. Computer Systems& Applications, 2016, 25(8): 135-138 |
| |
| Authors: | WANG Jun-Feng PEI Yan-Xia WANG Tao |
| |
| Affiliation: | School of Sciences, Xi''an University of Technology, Xi''an 710054, China,School of Sciences, Xi''an University of Technology, Xi''an 710054, China and School of Sciences, Xi''an University of Technology, Xi''an 710054, China |
| |
| Abstract: | CDD inpainting model is based on TV model local spread and it introduces curvature term, then realizes the connectivity and holistic principle. For the different size of the gradient value of each reference point and diffusion efficiency defects, an improved CDD inpainting algorithm is proposed by degenerate diffusion model. Firstly, it calculates the gradient information of pixel and curvature of isolux line to control the contribution of the reference point on the repair area, and then they are weighted. Finally, the discrete model of partial differential equations is given. Experimental results show that this algorithm realizes the connectivity principle partially. In addition, it can repair the damaged image better than CDD algorithm with same iterative times. |
| |
| Keywords: | image inpainting degenerate diffusion curvature-driven diffusion gradient anisotropic |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
