保细节自适应超分辨率融合算法

Adaptive Super-Resolution Fusion Algorithm with Detail Preserving

超分辨率融合是把配准好的低分辨率图像信息进行综合,形成高分辨率栅格上的均匀采样为了改善图像超分辨率融合效果,对鲁棒超分辨率融合算法进行改进.分析图像局部模式,给出角点和连接点的识别方法,进而设计了保细节自适应适用度函数,提出了保细节自适应超分辨率融合算法.实验结果表明,算法不仅对配准误差具有鲁棒性,而且能很好地保存图像的边缘和细节特征,提高了融合图像的质量.

Super-resolution fusion is to synthesize the information of low resolution images registrated and to construct the uniformed samples of high resolution grid. To improve the effect of super-resolution image fusion,an improved approach was proposed on the basis of robust super-resolution fusion. Through the analysis of the local mode of image and the way to recognize the comer and junction,the adaptive applicability function with detail preserving was designed and the adaptive super-resolution fusion algorithm was proposed. Experimental results show that the proposed adaptive super-resolution fusion algorithm with detail preserving is robust to registration error and can keep the features of edge and the detail of image well ,which improves the equality of fused image.