###
计算机系统应用:2020,29(3):100-107
本文二维码信息
码上扫一扫!
基于深度学习的齿轮视觉微小缺陷检测
(1.福建师范大学 光电与信息工程学院, 福州 350007;2.医学光电科学与技术教育部重点实验室, 福州 350007)
Visual Detection of Minor Gear Defect Based on Deep Learning
(1.College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou 350007, China;2.Key Laboratory of OptoElectronic Science and Technology for Medicine (Ministry of Education), Fuzhou 350007, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 495次   下载 233
投稿时间:2019-08-06    修订日期:2019-09-05
中文摘要: 针对齿轮视觉微小缺陷,采用一种基于深度学习算法的Mask R-CNN网络进行检测,并对网络进行相应地优化调整.首先,通过比较5种残差神经网络检测效果,选择resnet-101作为图像共享特征提取网络.然后,剔除特征金子塔网络中对特征图P5进行的不合理的3×3卷积,缺齿检出率指标相应得到提升.最后,为了对候选区域网络进行有效的训练,根据设计的样本标注方案中小范围波动的标注尺寸,设置合适的anchors大小以及宽高比.最终,经过优化的Mask R-CNN网络达到了98.2%缺齿检出率.
Abstract:The optimized Mask R-CNN network based on deep learning is used to visual detection of the tiny defects on gears. Firstly, by comparing the detection effects of five kinds of residual neural network, resnet-101 is selected as the image sharing feature extraction network. Then, the detection rate for missing tooth is correspondingly improved by eliminating the unreasonable 3×3 convolution of feature map P5 in the feature pyramid network. Finally, in order to effectively train the region proposal network, the appropriate anchor size and aspect ratio are set according to small fluctuation of annotation box in the designed sample labeling scheme. The optimized Mask R-CNN network eventually achieved 98.2% detection rate for missing tooth on gears.
文章编号:7323     中图分类号:    文献标志码:
基金项目:中央引导地方科技发展专项(2017L3009)
引用文本:
韩明,吴庆祥,曾雄军.基于深度学习的齿轮视觉微小缺陷检测.计算机系统应用,2020,29(3):100-107
HAN Ming,WU Qing-Xiang,ZENG Xiong-Jun.Visual Detection of Minor Gear Defect Based on Deep Learning.COMPUTER SYSTEMS APPLICATIONS,2020,29(3):100-107

用微信扫一扫

用微信扫一扫