结合频率和ViT的工业产品表面相似特征缺陷检测方法  

Defect detection method for industrial product surfaces with similar features by combining frequency and ViT

作　　者：王素琴[1] 程成[1] 石敏[1] 朱登明[2,3] Wang Suqin;Cheng Cheng;Shi Min;Zhu Dengming(School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;Taicang-ZK Institute of Information and Technology,Taicang 215400,China)

机构地区：[1]华北电力大学控制与计算机工程学院,北京102206 [2]中国科学院计算技术研究所,北京100190 [3]太仓中科信息技术研究院,太仓215400

出　　处：《中国图象图形学报》2024年第10期3074-3089,共16页Journal of Image and Graphics

基　　金：国家重点研发计划资助(2020YFB1710400);国家自然科学基金项目(61972379)。

摘　　要：目的工业产品表面的缺陷检测是保证其质量的重要环节。针对工业产品表面缺陷与背景相似度高、表面缺陷特征相似的问题,提出了一种差异化检测网络YOLO-Differ(you only look once-difference)。方法该网络以YOLOv5(you only look once version 5)为基础,利用离散余弦变换算法和自注意力机制提取和增强频率特征,并通过融合频率特征,增大缺陷与背景特征之间的区分度;同时考虑到融合中存在的错位问题,设计自适应特征融合模块对齐并融合RGB特征和频率特征。其次,在网络的检测模块后新增细粒度分类分支,将视觉变换器(vision Transformer,ViT)作为该分支中的校正分类器,专注于提取和识别缺陷的微小特征差异,以应对不同缺陷特征细微差异的挑战。结果实验在3个数据集上与7种目标检测模型进行了对比,YOLO-Differ模型均取得了最优结果,与其他模型相比,平均准确率均值(mean average precision,mAP)分别提升了3.6%、2.4%和0.4%以上。结论YOLO-Differ模型与同类模型相比,具有更高的检测精度和更强的通用性。Objective In industrial production,influenced by the complex environment during manufacturing and production processes,surface defects on products are difficult to avoid.These defects not only destroy the integrity of the products but also affect their quality,posing potential threats to the health and safety of individuals.Thus,defect detection on the surface of industrial products is an important part that cannot be ignored in production.In defect detection tasks,the targets must be accurately classified to determine whether they should be subjected to recycling treatment.At the same time,the detection results must be presented in the form of bounding boxes to assist enterprises in analyzing the causes of defects and improving the production process.The traditional method of surface defect detection is the manual inspection method.However,in practice,manual inspection often has large limitations.In recent years,the performance of computers has improved by leaps and bounds,and traditional machine vision technology has been widely tested in various production fields.These methods rely on image processing and feature engineering,and in specific scenarios,they can reach a level close to manual detection,truly realizing the productivity replacement of machines for some manual labor.However,the shortcoming is the difficulty in extracting features from complex backgrounds,often resulting in inaccurate detection.Therefore,it is hardly reused in other types of workpiece inspection tasks.Deep learning has played an increasingly important role in the field of computer vision in recent years.Deep learning-based defect detection methods learn the features of numerous defect samples and utilize the defect sample features to achieve classification and localization.With high detection accuracy and applicability,they have addressed the complexity and uncertainty associated with manual feature extraction in traditional image processing,achieving remarkable results in industrial product surface defect detection.However,given the

关 键 词：表面缺陷检测 相似性 频率特征 细粒度分类 通用性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]