摘要
提出一种基于高阶统计量和图像分割技术的改进的非负支持域递归逆滤波算法(NAS-RIF)。该算法应用高阶统计量去噪,解决了原NAS-RIF算法敏感于噪声的特性,提高了退化图像的信噪比。其次,在每次迭代中利用图像分割技术进行图像支持域的自估计,改变了NAS-RIF算法中支持域必须是方形的不利限制。实验结果表明改进的NAS-RIF算法具有更好的噪声抑制和边缘细节恢复效果。
An improved nonnegativity and support constraints recursive inverse filtering（ NAS-RIF） algorithm based on high-order statistics and image segmentation is presented. The algorithm applies high-order statistics in denoising and overcomes the character of noise sensitivity in original NAS-RIF,and improves the PSNR of image as well. Next,the image segmentation is used in each iteration to self-estimate the image support domain,this changes the detrimental limitation that in NAS-RIF algorithm the support domains have to be the square.Experimental results demonstrate that the improved NAS-RIF algorithm has better effect in noise suppression and edge details restoration.
出处
《计算机应用与软件》
CSCD
北大核心
2014年第8期222-224,297,共4页
Computer Applications and Software
基金
河南省教育厅自然科学基金项目(2010C520020)
