Miao Xikui, Zhao Wei, Li Xiaolong, Yang Xiaoyu
Appl Opt. 2019 Aug 20;58(24):6504-6512. doi: 10.1364/AO.58.006504.
Local binary pattern (LBP) and its derivates have been widely used in texture classification. However, LBP-based methods are sensitive to noise, and some structure information represented by non-uniform patterns is lost due to the combination of these patterns. In this paper, a new local structure descriptor based on just noticeable difference (JND) for texture classification is proposed by exploring the spatial and relative intensity correlations among local neighborhood pixels. First, a JND map of the image is computed, and then we attempt to model the correlations among local neighborhood pixels by comparing the absolute differences in intensity between the central pixel and its neighbors with the corresponding JND threshold. A new visual pattern (JNDVP) is designed using modeled correlations to describe image structure. Next, considering that image contrast makes important contributions to structure description, contrast is employed as a weighting factor for JNDVP histogram creation to represent structural and contrast information in a single representation. Finally, the nearest neighborhood classifier is employed for texture classification. Results on two texture image databases demonstrate that the proposed structure descriptor is rotation invariant and more robust to noise than LBP. Moreover, texture classification based on JNDVP outperforms LBP-based methods.
局部二值模式（LBP）及其衍生方法已在纹理分类中得到广泛应用。然而，基于LBP的方法对噪声敏感，并且由于这些模式的组合，一些由非均匀模式表示的结构信息会丢失。本文通过探索局部邻域像素之间的空间和相对强度相关性，提出了一种基于恰可察觉差异（JND）的新型局部结构描述符用于纹理分类。首先，计算图像的JND图，然后我们尝试通过将中心像素与其邻居之间的强度绝对差值与相应的JND阈值进行比较，来对局部邻域像素之间的相关性进行建模。利用建模后的相关性设计了一种新的视觉模式（JNDVP）来描述图像结构。接下来，考虑到图像对比度对结构描述有重要贡献，将对比度用作创建JNDVP直方图的加权因子，以便在单一表示中同时呈现结构和对比度信息。最后，采用最近邻分类器进行纹理分类。在两个纹理图像数据库上的实验结果表明，所提出的结构描述符具有旋转不变性，并且比LBP对噪声更具鲁棒性。此外，基于JNDVP的纹理分类优于基于LBP的方法。
