摘要
图像修复是一个基于周围未被损坏信息对图像中丢失或损坏信息进行修补的过程。提出了一个基于Navier-Stokes方程的新的图像修复算法。该算法能够同时在修复区域内部进行信息的填充,而在修复区域外部去除噪声(如果存在)。实验结果表明模型对于图像中划痕,信息丢失,甚至移除整个景物都是有效的。
Image inpainting is the process of filling in missing parts of damaged images based on information gleaned from surrounding areas.A new algorithm for inpainting based on the Navier-Stokes equation,which allows for inpainting inside of the inpainting region and denoising outside of the inpainting region,is outlined.The experimental results show the effective performance of the proposed model in restoring scratched photos,missing parts and even removal of entire objects from images.
出处
《中山大学学报(自然科学版)》
CAS
CSCD
北大核心
2012年第1期9-13,18,共6页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
国家自然科学基金资助项目(10971234)
国家自然科学基金天元基金资助项目(11026227)
中央高校基本科研业务费专项基金资助项目(10lgzd09)
广州市科技计划资助项目(2010C6-I00011)