Directional textures auto-inspection using principal component analysis
Directional textures auto-inspection using principal component analysis
复制标题
DOI：
10.1007/s00170-010-3141-1
复制
发表时间：
2011-01
期刊：
影响因子：
--
通讯作者：
Ssu-Han Chen;D. Perng
中科院分区：
文献类型：
--
作者：
Ssu-Han Chen;D. Perng
本文描述了一种使用主成分分析的全局图像恢复方案，可用于自动检查定向纹理表面的缺陷。将图像像素的灰度级分解为行向量的集合，将输入的空域图像变换到主成分空间，使得方向纹理由第一个主成分及其相应的权向量很好地近似，称为截断成分解（TCS）。然后通过在原始图像和 TCS 之间应用图像减法来揭示局部缺陷。此过程模糊所有方向纹理并仅保留最初嵌入输入图像中的局部缺陷。这些缺陷（如果有）最终通过阈值提取。在具有方向纹理（例如直线、倾斜、正交、倾斜正交和倾斜线性图元）的各种产品表面上进行了实验，以证明该方法的有效性和鲁棒性。此外，还进行了一些初步实验，以证明所提出的方案对水平和垂直移位、光照变化和图像旋转不敏感。
This paper describes a global image restoration scheme using a principal component analysis that can be used to inspect defects in directional textured surfaces automatically. Decomposing the gray level of image pixels into an ensemble of row vectors, the input spatial domain image is transformed into principal component space so that the directional textures are well approximated by firstkmajor components and their corresponding weight vectors, named truncated component solution (TCS). Then the local defects will be revealed by applying image subtraction between the original image and the TCS. This procedure blurs all directional textures and preserves only the local defects that were initially embedded in the input image. These defects, if any, are finally extracted by thresholding. Experiments on a variety of product surfaces with directional textures such as straight, slanted, orthogonal, slanted orthogonal, and oblique linear primitives were conducted to demonstrate the effectiveness and robustness of the proposed method. Furthermore, some preliminary experiments were also conducted to demonstrate the proposed scheme was insensitive to horizontal and vertical shifting, changes in illumination, and image rotation.