摘要
将基于偏微分方程的修补模型中的曲率因素应用于样本修补模型,提出了曲率驱动的基于样本的图像修补模型,改善了具有曲线形状的修补区域的修补效果.实验结果表明,改进的方法对于待修补区域周围具有曲线形状的图像修补有着良好的效果.
In this paper, to improve the performance of the model on big targeted area around of curve shape, we proposed a new curvature - driven examplar - based image inpainting model using the factor of curvature which is often used in PDE based image. As is domenstrated by the experimental results, the proposed method has good performance on big targed around area of curve shape.
出处
《福州大学学报（自然科学版）》
CAS
CSCD
北大核心
2012年第3期322-326,共5页
Journal of Fuzhou University(Natural Science Edition)
基金
国家自然科学基金资助项目(11071270)
福建省自然科学基金资助项目(2010J01328)
关键词
图像修补
偏微分方程
样本
曲率驱动
image inpainting
partial differential equation
exemplar
curvature driven
