摘要
为解决传统图像插值算法存在的边缘模糊和边缘锯齿,提出了一种基于像素点模糊隶属度的图像自适应插值方法.该方法首先根据图像的梯度与相角特性,确定像素点的模糊隶属度,再根据图像的局部不对称性在一维方向上修正插值点空间距离,并将一维修正结果转化到二维图像空间,最终将修正后的空间距离应用到传统双线性插值和双立方插值中.实验结果表明,该算法改善了图像的信噪比,有效抑制了边缘锯齿和边缘模糊的发生.
Conventional image interpolation algorithm always introduces the the blur and jagged edges.To solve this problem,an improved adaptive image interpolation algorithm with using membership function is proposed in this paper.Fuzzy logic is used to obtain the membership function with the local characteristics of the gradient and phase angle.The first step is to correct the special distance of interpolated pixels along one dimension in the basis of local asymmetry features and the membership function,and then to convert the corrected distance of one dimension into two dimensions,applying the corrected distance to conventional image interpolation algorithm.Experimental results demonstrate that the improved algorithm can produce better results in regard to the signal-to-nosie ratio and succeed in preserving interpolation image edges in various directions.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2010年第11期7535-7539,共5页
Acta Physica Sinica
基金
国家高技术研究发展计划(批准号:2007AA701206)资助的课题~~
关键词
模糊隶属度
空间距离
图像插值
membership function
distance
image interpolation
