Nonlocal Edge-Directed Interpolation
Nonlocal Edge-Directed Interpolation
复制标题
DOI：
10.1007/978-3-642-10467-1_121
复制
发表时间：
2009-12
期刊：
影响因子：
--
通讯作者：
Xinfeng Zhang;Siwei Ma;Yongbing Zhang;Li Zhang;Wen Gao
中科院分区：
文献类型：
--
作者：
Xinfeng Zhang;Siwei Ma;Yongbing Zhang;Li Zhang;Wen Gao
本文提出了一种新的边缘定向图像内插算法，该算法能有效地保留图像的边缘特征和自然外观。该方法首先利用自回归模型(AR)和低分辨率图像与高分辨率图像之间的几何对偶关系，得到最小均方误差意义下最优插值系数的闭合解，然后利用图像的结构相似性得到非局部边缘定向插值法(NLEDI)的系数，即加权最小二乘方程的解。与已有的方法相比，新的图像内插方法更好地保持了内插图像的空间相干性，并且在主客观图像质量方面都优于其他方法。
In this paper, we proposed a new edge-directed image interpolation algorithm which can preserve the edge features and natural appearance of images efficiently. In the proposed scheme, we first get a close-form solution of the optimal interpolation coefficients under the sense of minimal mean square error by exploiting autoregressive model (AR) and the geometric duality between the low-resolution and high-resolution images .Then the coefficients of the Nonlocal Edge-directed interpolation (NLEDI) are derived with structure similarity in images, which are solutions of weighted least square equations. The new image interpolation approach preserves spatial coherence of the interpolated images better than the existing methods and it outperforms the other methods in terms of objective and subjective image quality.