摘要
线性插值算法容易产生细节模糊和边缘锯齿效应,为了较好地保持图像的边缘信息,改善图像的主观视觉效果,提出了一种改进的Warped Distance (WaDi)图像插值方法。传统的WaDi算法是对空间线性插值的改进,但它仅仅利用了图像边缘的局部不对称特征来计算WaDi。除了局部不对称特征,局部梯度特征也是图像边缘的一种重要特征。文中采用将局部不对称特征和局部梯度特征相结合的方法来计算WaDi,可同时保持图像边缘的细节特征和非边缘的光滑性。实验结果表明,用该方法能获得高精度的插值图像。
The smooth effect and zigzagging artifacts are inevitable during linear interpolation, In this paper, propose an improved warped distance （WaDi） image interpolation to preserve edge information and improve visual quality. The conventional WaDi algorithm is improvement of the spatial linear interpolation, However, it uses only the local asymmetry features of image edges to compute the WaDi, The local gradient features are also one kind of the important features of image edges, In this paper,adopt both the local asymmetry features and the local gradient features in the WaDi computation. The algorithm can effectively preserve edges while maintaining the smoothness of nonedges. Experimental results show that the proposed method can obtain high accuracy interpolated images.
出处
《计算机技术与发展》
2008年第6期76-78,82,共4页
Computer Technology and Development
