基于掩膜迭代ROI改进LBP算法的齿轮缺陷检测方法研究  

Research on gear defect detection method based on mask iterative ROI improved LBP algorithm

作　　者：王岩[1,3] 胡睿甫 吕传景 董颖怀 付志强[4] 栾琦[1] WANG Yan;HU Ruifu;LYU Chuanjing;DONG Yinghuai;FU Zhiqiang;LUAN Qi(Laboratory of Advanced Materials Precision Manufacturing and Special Processing,College of Mechanical Engineering,Tianjin University of Science and Technology,Tianjin 300222,China;Zhengzhou Chenwei Technology Co.,Zhengzhou,Henan 450000,China;Tianjin Key Laboratory of Integrated Design and Online Monitoring of Light Industry and Food Engineering Machinery and Equipment,Tianjing 300222,China;College of Light Industry Science and Engineering,Tianjin University of Science and Technology,Tianjin 300222,China)

机构地区：[1]天津科技大学机械工程学院先进材料精密制造与特种加工实验室,天津300222 [2]郑州辰维科技股份有限公司,河南郑州450000 [3]天津市轻工与食品工程机械装备集成设计与在线监控重点实验室,天津300222 [4]天津科技大学轻工科学与工程学院,天津300222

出　　处：《光电子．激光》2024年第12期1276-1283,共8页Journal of Optoelectronics·Laser

基　　金：天津市自然科学基金(19JCZDJC33200,18JCQNJC05200,18JCYBJC88900);天津市教委科研计划项目(2018KJ116)资助项目。

摘　　要：为提高传统局部二值模式(local binary pattern,LBP)算法提取目标图像特征时的识别率,提出一种基于掩膜迭代感兴趣区域(region of interest,ROI)改进LBP算法的特征提取方法。使用掩膜迭代ROI的提取方法,减少对干扰信息或者无效区域的处理,缩短缺陷区域的提取时间。在LBP的基础上根据预设的半径确定所述中心像素点的圆形区域,将邻域采样点之间的灰度值大小关系加入考虑范围,与中心阈值共同作为决定LBP编码情况的影响因子,充分利用邻域点之间所隐藏的方向特征,进一步提高了图像识别的准确率。实验表明,以PASCAL VOC齿轮缺陷数据集中缺陷图像为验证样本,实验所拍摄缺陷图像由SVM识别准确率相较传统LBP算法提升2%,最高识别率99.32%;Manhattan识别准确率相较传统LBP算法提升0.67%,最高识别率98.54%;European识别准确率相较传统LBP算法提升0.44%,最高识别率97.87%。In order to improve the recognition rate of the traditional local binary pattern(LBP)algorithm when extracting target image features,a feature extraction method based on mask iterative region of interest(ROI)to improve the LBP algorithm is proposed.The extraction method using mask iterative ROI reduces the processing of interference information or invalid regions and shortens the extraction time of defective region.Based on the LBP,the circular area of the said central pixel point is determined according to the preset radius,the gray value size relationship between the neighboring sampling points is added into the consideration,and together with the central threshold,it is used as the influence factor to decide the LBP coding situation,and the directional features hidden between the neighboring points are fully utilized to further improve the accuracy of image recognition,and the experimental results show that using the PASCAL VOC gear defect dataset as the validation sample,the defect images captured in the experiment show a 2%improvement with SVM recognition accuracy compared with traditional LBP algorithm,with a maximum recognition rate of 99.32%.The Manhattan recognition accuracy improves by 0.67%compared with traditional LBP algorithm,with a maximum recognition rate of 98.54%.The European recognition accuracy improves by 0.44%compared with traditional LBP algorithm,with a maximum recognition rate of 97.87%.

关 键 词：齿轮 感兴趣区域(ROI) 局部二值模式(LBP) LBP编码 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]