一种基于级联RCNN的织物瑕疵检测算法  

FABRIC DEFECT DETECTION ALGORITHM BASED ON CASCADE RCNN

作　　者：赵玉香 段先华 赵楚 Zhao Yuxiang;Duan Xianhua;Zhao Chu(College of Computer,Jiangsu University of Science and Technology,Zhenjiang 212000,Jiangsu,China)

机构地区：[1]江苏科技大学计算机学院,江苏镇江212000

出　　处：《计算机应用与软件》2024年第11期241-246,共6页Computer Applications and Software

基　　金：国家自然科学基金项目(61806087);江苏省研究生创新项目(SJCX20_1475)。

摘　　要：为了识别织物中的瑕疵,减少经济损失,针对现有一些网络检测方法存在检测精度不高以及对小目标检测不灵敏的问题,提出一种基于级联RCNN织物瑕疵算法ZS-Cascade RCNN。首先,在特征提取阶段,加入可变形卷积,保留特征的完整性;其次,调整锚框来适应不同纵横比的瑕疵检测需求,提高检测效果;最后,采用交并比均衡采样,均衡正负样本。实验表明,ZS-Cascade RCNN算法比原始算法准确率提高4.5百分点,平均精度提升17.8百分点,对织物瑕疵检测效果有明显提升。In order to identify fabric defects and reduce economic losses,aiming at the problems of low detection accuracy and insensitivity to small target detection in some existing network detection methods,this paper proposes a fabric defect algorithm ZS-Cascade RCNN based on cascade RCNN.In the feature extraction stage,deformable convolution was added to preserve the integrity of feature.The anchor frame was adjusted to meet the defect detection requirements of different aspect ratios to improve the detection effect.The cross and parallel ratio equalization sampling was used to equalize positive and negative samples.Experimental results show that the accuracy of ZS-Cascade RCNN algorithm is 4.5 percentage points higher and the average accuracy is 17.8 percentage points higher than that of the original algorithm.The effect of fabric defect detection is obviously improved.

关 键 词：卷积神经网络 深度学习 瑕疵检测 级联检测器 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]