基于U型Swin Transformer自编码器的色织物缺陷检测  

Yarn-Dyed Fabric Defect Detection Based on U-Shaped Swin Transformer Auto-Encoder

作　　者：黄媛媛 熊文博 张宏伟[1,2] 张伟伟 Huang Yuanyuan;Xiong Wenbo;Zhang Hongwei;Zhang Weiwei(School of Electronic Information,Xi’an Polytechnic University,Xi’an 710048,Shaanxi,China;State Key Laboratory of Industrial Control Technology,Zhejiang University,Hangzhou 310027,Zhejiang,China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048 [2]浙江大学工业控制技术国家重点实验室,浙江杭州310027

出　　处：《激光与光电子学进展》2023年第12期293-300,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61803292);中国纺织工业联合会科技指导性项目(2020111);工业控制技术国家重点实验室开放课题(ICT2021B04);陕西省科技厅面上项目(2019JM-263)。

摘　　要：针对传统卷积神经网络对色织物花型缺陷检测效果不佳的问题,提出一种基于U型Swin Transformer重构模型和残差分析的缺陷检测方法。该方法使用Transformer模型,可更好地实现对图像全局特征的提取以及更准确的重构,同时解决了实际生产过程中缺陷样本数量少且种类不平衡的问题。首先,针对某种花型,采用叠加噪声后的无缺陷样本完成重构模型的训练过程;然后,将待测图像输入模型中获得重构图像;接着,计算待测图像和重构图像的残差图像;最后,通过阈值分割和数学形态学处理,即可实现对缺陷区域的检测和定位。实验结果表明,该方法在不需要对缺陷样本标记的情况下,能够有效地检测和定位多个色织物花型上的缺陷区域。Considering the non-effectiveness of traditional convolution neural networks in detecting pattern defects in yarndyed fabrics,a defect detection method based on a U-shaped Swin Transformer reconstruction model and residual analysis is proposed.This method uses the Transformer model to improve the extraction of global image features and enhance reconstruction while solving for the small number and unbalanced types of defective samples during the actual production process.First,the training process of the reconstructed model is completed for a certain pattern using the non-defective samples after adding noise.Subsequently,the test image is inputted into the model to obtain the reconstructed image,and its residual image and reconstructed image are calculated.Finally,the defect areas are detected and located via threshold segmentation and mathematical morphology processing.The results indicate that this method can be effectively used for the detection and location of defect areas on multiple yarn-dyed fabric patterns without requiring the marking of the defective samples.

关 键 词：机器视觉 图像处理 色织物 缺陷检测 无监督学习 Swin Transformer 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]