Xu Panpan, Wang Wencheng
IEEE Trans Image Process. 2018 Mar 28. doi: 10.1109/TIP.2018.2820427.
Texture filtering depends on high-quality texture measurement to separate structures from textures. However, the existing methods employ axis-aligned box windows for texture measurement, which may cover different texture regions, and so lowering the measurement quality because structure edges are not always parallel to the axes. Additionally, the existing texture measurements consider intensity contrast at the pixel level and do not account for the linear characteristics of structure edges in filtering windows; thus, their measurement effectiveness is limited. This results in a dilemma for texture filtering. Large-scale textures are not smoothed using smaller windows, while small structures are removed using larger windows. In this paper, we present edge-aware measures to improve texture measurement. Edge-aware windows are constructed such that each window is inside a texture region to the greatest extent possible, and the linear characteristics of structure edges are accounted for in the texture measurement. Furthermore, we use large box windows for texture filtering and long and narrow edge-aware small windows for texture measurement to filter out large-scale textures while preserving small structures. The experimental results show improved texture filtering with our method compared with existing methods.
纹理滤波依赖于高质量的纹理测量来将结构与纹理分离。然而，现有方法采用轴对齐的矩形窗口进行纹理测量，这可能会覆盖不同的纹理区域，从而降低测量质量，因为结构边缘并不总是与坐标轴平行。此外，现有的纹理测量考虑的是像素级别的强度对比度，在滤波窗口中没有考虑结构边缘的线性特征；因此，它们的测量效果有限。这导致了纹理滤波的两难境地。使用较小的窗口无法平滑大规模纹理，而使用较大的窗口会去除小结构。在本文中，我们提出了边缘感知测量方法来改进纹理测量。构建边缘感知窗口，使得每个窗口尽可能最大程度地位于纹理区域内，并且在纹理测量中考虑结构边缘的线性特征。此外，我们使用大的矩形窗口进行纹理滤波，使用长而窄的边缘感知小窗口进行纹理测量，以在保留小结构的同时滤除大规模纹理。实验结果表明，与现有方法相比，我们的方法改进了纹理滤波。
