-
摘要: 提出了一种新的基于Lp范数的自适应偏微分方程图像处理模型, 改进了Tony Chan的TV变分模型和张红英的p-Laplace模型. TV模型对图像采用全局约束, 而新的扩散方程在图像不同的位置上采用不同的约束, 具有局部自适应的特性, 在扩散的同时更好地保持了图像的边缘信息, 进而将其应用到图像恢复(去噪, 去除模糊)中去. 实验结果表明新模型的综合性能优于Tony Chan和张等现有的模型.Abstract: A new Lp regulation based PDE image processing model is proposed to improve the TV model by Tony Chan and the p-Laplace method by Zhang. The new model adopts adaptive regulation at different pixels of the image, in contrast to the TV method using a global regulation, so that it keeps the detail information such as edges better while diffuses the flat regions. Numerical experiments on image denoising, deblurring and inpainting are given to show that the new model is superior to the existing models.
-
Key words:
- Partial differential equations (PDE) /
- Lp norm /
- image denoising /
- image restoration
-
点击查看大图
计量
- 文章访问数: 2176
- HTML全文浏览量: 71
- PDF下载量: 2485
- 被引次数: 0
下载:
