| 黄森林,王耀南,彭玉,周显恩,严佳栋,范涛,刘学兵,刘远强.基于迟滞阈值分割的瓶口缺陷检测方法[J].电子测量与仪器学报,2017,31(8):1289-1296 |
| 基于迟滞阈值分割的瓶口缺陷检测方法 |
| Bottle mouth defect detection method based on hysteresis thresholding segmentation |
| |
| DOI：10.13382/j.jemi.2017.08.018 |
| 中文关键词: 机器视觉 迟滞阈值分割 随机圆检测 缺陷检测 |
| 英文关键词:machine vision hysteresis thresholding segmentation random testing defect detection |
| 基金项目:国家自然科学基金（61573134）资助项目 |
|
|
| Author | Institution |
| Huang Senlin | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Wang Yaonan | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Peng Yu | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Zhou Xian’en | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Yan Jiadong | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Fan Tao | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Liu Xuebing | National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha 410082, China |
| Liu Yuanqiang | Foshan Xiangde Intelligent Technology Co. Ltd., Foshan 528000, China |
|
| 摘要点击次数: 3628 |
| 全文下载次数: 15594 |
| 中文摘要: |
| 随着工业机器人和现代化工业的快速发展，人们对工业机器人的性能要求越来越高，为了提高工业生产的效率和产品的质量，智能、高速、高精度是工业机器人的必备要求。国内基于机器视觉的智能啤酒瓶口缺陷检测方法中，高速、高精度仍是一个亟待解决的问题。为此，提出了一种基于随机圆拟合评估的四圆周定位法，大大提高了瓶口检测区域的定位精度，并提出了基于投影特征的分区域磁滞阈值分割的智能瓶口缺陷检测方法。对采集的488幅灰度图像进行测试，检测正确率为99.4%，检测平均速度为38 ms，算法的检测速度快，检测精度高，可以很好地应用到高速、高精度的现代化工业机器人中。 |
| 英文摘要: |
| With the development of industrial robots and modern industrial, the more performance requirements for industrial robots are needed. To improve production efficiency and product quality, intelligent, high speed and high precision are essential requirements for industrial robots. In summary of domestic intelligent beer bottle mouth defect detection method based on machine vision, high speed and high accuracy is still a problem to be solved. This paper presents the four circle positioning method based on circle fitting assessment method, which greatly improves the accuracy of bottle mouth detection area, and the smart bottle mouth defects detection method based on sub region hysteresis thresholding segmentation of projection features. Collected 488 image tests, the detection accuracy is 99.4%, the average speed of detection is 38 ms. The algorithm proposed in this paper has high detection speed and high detection precision, it can be well applied in the modern industrial robot with high speed and high precision. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
