Automated surface inspection (ASI) is a challenging task in industry, as collecting training dataset is usually costly and related methods are highly dataset-dependent. In this paper, a generic approach that requires small training data for ASI is proposed. First, this approach builds classifier on the features of image patches, where the features are transferred from a pretrained deep learning network. Next, pixel-wise prediction is obtained by convolving the trained classifier over input image. An experiment on three public and one industrial data set is carried out. The experiment involves two tasks: 1) image classification and 2) defect segmentation. The results of proposed algorithm are compared against several best benchmarks in literature. In the classification tasks, the proposed method improves accuracy by 0.66%–25.50%. In the segmentation tasks, the proposed method reduces error escape rates by 6.00%–19.00% in three defect types and improves accuracies by 2.29%–9.86% in all seven defect types. In addition, the proposed method achieves 0.0% error escape rate in the segmentation task of industrial data.

中文翻译：

---

基于通用深度学习的自动表面检测方法

自动表面检查（ASI）在行业中是一项艰巨的任务，因为收集训练数据集通常很昂贵，并且相关方法高度依赖于数据集。在本文中，提出了一种通用方法，该方法需要针对ASI的少量训练数据。首先，这种方法基于图像补丁的特征建立分类器，其中特征是从预训练的深度学习网络转移而来的。接下来，通过将训练后的分类器卷积在输入图像上来获得逐像素预测。对三个公共数据集和一个工业数据集进行了实验。实验涉及两个任务：1）图像分类和2）缺陷分割。将该算法的结果与文献中的几种最佳基准进行了比较。在分类任务中，提出的方法将准确性提高了0.66％–25.50％。在分割任务中，所提出的方法在三种缺陷类型中将错误逃逸率降低了6.00％–19.00％，在所有七种缺陷类型中将准确性提高了2.29％–9.86％。另外，该方法在工业数据分割任务中达到了0.0％的错误逃逸率。