Surface Defects Detection of Paper Dish based on Mask R-CNN

机译：基于Mask R-CNN的纸碟表面缺陷检测

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Machine vision is widely used in the detection of surface defects in industrial products. However, traditional detection algorithms are usually specialized and cannot be generalized to detect all types of defects. Object detection algorithms based on deep learning have powerful learning ability and can identify various types of defects. This paper applied object detection algorithm to defects detection of paper dish. We first captured the images with different shapes of defects. Then defects in these images were annotated and integrated for model training. Next, the model Mask R-CNN were trained for defects detection. At last, we tested the model on different defects categories. Not only the category and the location of the defect in the image could be got, but also the pixel segmentation were given. The experiments show that Mask R-CNN is a successful approach for defect detection task, which can quickly detect defects with a high accuracy.

机译：机器视觉广泛用于检测工业产品的表面缺陷。但是，传统的检测算法通常是专门的，不能推广到检测所有类型的缺陷。基于深度学习的目标检测算法具有强大的学习能力，可以识别各种类型的缺陷。本文将目标检测算法应用于纸碟缺陷检测中。我们首先捕获了具有不同形状缺陷的图像。然后注释这些图像中的缺陷并进行集成以进行模型训练。接下来，模型Mask R-CNN被训练用于缺陷检测。最后，我们在不同的缺陷类别上测试了该模型。不仅可以获得图像中缺陷的类别和位置，而且给出了像素分割。实验表明，Mask R-CNN是一种成功的缺陷检测方法，可以快速，高精度地检测缺陷。

著录项

来源
《Third International Workshop on Pattern Recognition》|2018年|108280S.1-108280S.6|共6页
会议地点 Jinan(CN)
作者
Xuelong Wang; Ying Gao; Junyu Dong; Xukun Qin; Lin Qi; Hui Ma; Jun Liu;
展开▼
作者单位

College of Information Science and Engineering, Ocean University of China, Qingdao, China;

College of Information Science and Engineering, Ocean University of China, Qingdao, China;

College of Information Science and Engineering, Ocean University of China, Qingdao, China;

University of Minnesota Twin Cities, USA;

College of Information Science and Engineering, Ocean University of China, Qingdao, China;

College of Information Science and Engineering, Ocean University of China, Qingdao, China;

College of Science and Information Science, Qingdao Agricultural University, Qingdao, China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Surface Defect Detection; Mask R-CNN; Deep learning;

机译：表面缺陷检测；遮罩R-CNN;深度学习;

相似文献

外文文献
中文文献
专利

1. Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN) [J] . Hao Zhenbang, Lin Lili, Post Christopher J., ISPRS Journal of Photogrammetry and Remote Sensing . 2021,第Auga期

机译：使用基于面具区域的卷积神经网络（面膜R-CNN）自动化树冠和高度检测
2. Probability-based Mask R-CNN for pulmonary embolism detection [J] . Long Kun, Tang Lei, Pu Xiaorong, Neurocomputing . 2021,第Jana21期

机译：基于概率的肺栓塞检测掩模R-CNN
3. The effect of data augmentation and network simplification on the image-based detection of broccoli heads with Mask R-CNN [J] . Pieter M. Blok, Frits K. van Evert, Antonius P. M. Tielen, Journal of Robotic Systems . 2021,第1期

机译：数据增强和网络简化对掩模R-CNN的基于图像的基于图像的检测的影响
4. Surface Defects Detection of Paper Dish based on Mask R-CNN [C] . Xuelong Wang, Ying Gao, Junyu Dong, International Workshop on Pattern Recognition . 2018

机译：基于掩模R-CNN的纸盘检测表面缺陷检测
5. Algorithms for vision-based defect detection on textured surfaces. [D] . Hou, Zhen. 2009

机译：在纹理表面上基于视觉的缺陷检测算法。
6. Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN [O] . Jiahao Shi, Zhenye Li, Tingting Zhu, 2020

机译：基于NAS和多通道面罩R-CNN的工业木质贴面的缺陷检测
7. Detection of Abandoned and Stolen Objects Based on Dual Background Model and Mask R-CNN [O] . Hyeseung Park, Seungchul Park, Youngbok Joo 2020

机译：基于双背景模型和掩模R-CNN的被遗弃和被盗对象的检测
8. Laser-based optical scattering detection of surface and subsurface defects in machined Si(sub 3)N(sub 4) components [R] . Sun, J. G. , Shirber, M. , Ellingson, W. A. , 1997

机译：基于激光的光学散射检测机加工si（sub 3）N（sub 4）组件中的表面和表面下缺陷

Surface Defects Detection of Paper Dish based on Mask R-CNN

摘要

著录项

相似文献

相关主题

期刊订阅