Fabric defect detection plays an important role in controlling the quality of textile production. In this article, a novel fabric defect detection algorithm is proposed based on a multi-scale convolutional neural network and low-rank decomposition model. First, multi-scale convolutional neural network, which can extract the multi-scale deep feature of the image using multiple nonlinear transformations, is adopted to improve the characterization ability of fabric images with complex textures. The effective feature extraction makes the background lie in a low-rank subspace, and a sparse defect deviates from the low-rank subspace. Then, the low-rank decomposition model is constructed to decompose the feature matrix into the low-rank part (background) and the sparse part (salient defect). Finally, the saliency maps generated by the sparse matrix are segmented based on an improved optimal threshold to locate the fabric defect regions. Experimental results indicate that the feature extracted by the multi-scale convolutional neural network is more suitable for characterizing the fabric texture than the traditional hand-crafted feature extraction methods, such as histogram of oriented gradient, local binary pattern, and Gabor. The adopted low-rank decomposition model can effectively separate the defects from the background. Moreover, the proposed method is superior to state-of-the-art methods in terms of its adaptability and detection efficiency.

中文翻译：

---

基于深度特征和低秩分解的织物疵点检测

织物疵点检测在控制纺织品生产质量方面起着重要作用。在本文中，提出了一种基于多尺度卷积神经网络和低秩分解模型的新型织物疵点检测算法。首先，采用多尺度卷积神经网络，利用多重非线性变换提取图像的多尺度深度特征，提高对复杂纹理织物图像的表征能力。有效的特征提取使得背景位于低秩子空间，稀疏缺陷偏离低秩子空间。然后构建低秩分解模型，将特征矩阵分解为低秩部分（背景）和稀疏部分（显着缺陷）。最后，稀疏矩阵生成的显着图基于改进的最优阈值进行分割，以定位织物缺陷区域。实验结果表明，多尺度卷积神经网络提取的特征比传统的手工特征提取方法更适合表征织物纹理，如定向梯度直方图、局部二值模式和Gabor等。采用的低秩分解模型可以有效地将缺陷与背景分离。此外，所提出的方法在适应性和检测效率方面优于最先进的方法。实验结果表明，多尺度卷积神经网络提取的特征比传统的手工特征提取方法更适合表征织物纹理，如定向梯度直方图、局部二值模式和Gabor。采用的低秩分解模型可以有效地将缺陷与背景分离。此外，所提出的方法在适应性和检测效率方面优于最先进的方法。实验结果表明，多尺度卷积神经网络提取的特征比传统的手工特征提取方法更适合表征织物纹理，如定向梯度直方图、局部二值模式和Gabor等。采用的低秩分解模型可以有效地将缺陷与背景分离。此外，所提出的方法在适应性和检测效率方面优于最先进的方法。