Purpose

The purpose of this paper is to present a novel method for minor fabric defects detection.

Design/methodology/approach

This paper proposes a PETM-CNN algorithm. PETM-CNN is designed based on self-similar estimation algorithm and Convolutional Neural Network. The PE (Patches Extractor) algorithm extracts patches that are possible to be defective patches to preprocess the fabric image. Then a TM-CNN (Triplet Metric CNN) method is designed to predict labels of the patches and the final label of the image. The TM-CNN can perform better than normal CNN.

Findings

This algorithm is superior to other algorithms on the data set of fabric images with minor defects. The proposed method achieves accurate classification of fabric images whether it has minor defects or not. The experimental results show that the approach is effective.

Originality/value

Traditional fabric defects detection is not effective as minor defects detection, so this paper develops a method of minor fabric images classification based on self-similar estimation and CNN. This paper offers the first investigation of minor fabric defects.

中文翻译：

---

基于CNN的次要织物缺陷检测

目的

本文的目的是提出一种检测织物次要缺陷的新方法。

设计/方法/方法

提出了一种PETM-CNN算法。基于自相似估计算法和卷积神经网络设计了PETM-CNN。PE（补丁提取器）算法提取可能是有缺陷的补丁的补丁，以对织物图像进行预处理。然后设计了TM-CNN（三重度量CNN）方法来预测斑块的标签和图像的最终标签。TM-CNN的性能比普通CNN更好。

发现

该算法在具有较小缺陷的织物图像数据集上优于其他算法。所提出的方法实现了织物图像的准确分类，无论其是否具有较小的缺陷。实验结果表明该方法是有效的。

创意/价值

传统的织物缺陷检测不能像次要缺陷检测一样有效，因此本文提出了一种基于自相似估计和CNN的次要织物图像分类方法。本文对织物的次要缺陷进行了首次调查。