基于机器视觉的酒液智能检测系统研究与开发

中国机械工程 ›› 2010, Vol. 21 ›› Issue (7): 766-772,821.

基于机器视觉的酒液智能检测系统研究与开发

周博文;王耀南;张辉;葛继

湖南大学,长沙,410082

出版日期:2010-04-10 发布日期:2010-04-16
基金资助:
国家自然科学基金资助项目(60835004，60775047)；国家863高技术研究发展计划资助项目(2007AA04Z244，2008AA04Z214)
National Natural Science Foundation of China（No. 60835004，60775047）;
National High-tech R&D Program of China (863 Program) （No. 2007AA04Z244，2008AA04Z214）

Research and Development on Intelligent Inspection System for Wine Based on Machine Vision

Zhou Bowen;Wang Yaonan;Zhang Hui;Ge Ji

Hunan University,Changsha,410082

Online:2010-04-10 Published:2010-04-16
Supported by:

National Natural Science Foundation of China（No. 60835004，60775047）;
National High-tech R&D Program of China (863 Program) （No. 2007AA04Z244，2008AA04Z214）

摘要/Abstract

摘要：

设计了一种基于机器视觉的酒液智能检测系统,主要用于酒液中杂质的在线检测。设计了系统的直线式检测机械结构和翻转机械手以及基于工控机和可编程控制器的控制系统,通过特定的给光方式和高速摄像机,获取酒液序列图像,采用亚像素边缘定位方法确定检测区域,提出了在检测区域里采用累积差分和基于空间最小交叉熵的阈值分割相结合的方法获取运动目标,根据运动轨迹判断目标是否为杂质,并对提取的杂质进行测量,计算是否在允许范围内。大量实验验证了检测算法的有效性和装置的可行性。



关键词:

机器视觉, 检测系统, 运动目标, 图像识别, 杂质测量

Abstract:

A machine-vision-based intelligent inspection system was presented.The linear convection mechanical structure and electric control system based on industrial computer and programmable logical controller were illustrated in detail.A method using high-speed cameras was applied for obtaining the image sequences.The sub-pixel edge location method was used for confirming the inspection region.The methods of cumulative difference and the minimum space of the cross-entropy threshold segmentation were used to acquire the moving targets.The foreign substances were judged by the moving trajectory.Finally,according to the metrical data of foreign substances,a robot gave an judgment that the product was qualified or unqualified. A great deal of experiments demonstrate that the detection algorithm is effective and the device is feasible.

Key words: machine vision, inspection system, moving target, image recognition, foreign substance measurement

中图分类号:

TP249

周博文, 王耀南, 张辉, 葛继.

基于机器视觉的酒液智能检测系统研究与开发

[J]. 中国机械工程, 2010, 21(7): 766-772,821.

ZHOU Bo-Wen, WANG Yao-Na, ZHANG Hui, GE Ji.

Research and Development on Intelligent Inspection System for Wine Based on Machine Vision

[J]. China Mechanical Engineering, 2010, 21(7): 766-772,821.

参考文献

[1]张玉红肖文龙.市售白酒抽检情况分析.黑河科技,2008,(1):41-42.
[2]李志斌[1].白酒中晶状沉淀的研究[J].酿酒,2008,35(5):44-46.
[3]黄新贵[1].提高瓶装白酒包装质量的技术措施[J].酿酒科技,2006(5):65-66.
[4]Duan Feng, Wang Yaonan, Liu Huanjun, et al. A Machine Vision Inspector for Beer Bottle[J]. Engineering Applications of Artificial Intelligence, 2007, 20(7):1013-1021.
[5]李杨果[1],王耀南[1],王威[1].基于机器视觉的大输液智能灯检机研究[J].光电工程,2006,33(11):69-74.
[6]Juan L, Yaonan W,Jie Z. On-line Detection of Foreign Substances in Glass Bottles Filled with Transfusion Solution through Computer Vision[C]//Proceedings of the 2008 IEEE International Conference on Information and Automation. Zhangjiajie, 2008: 424-429.
[7]杨福刚[1],孙同景[1],宋松林[2].基于机器视觉的全自动灯检机关键技术研究[J].仪器仪表学报,2008,29(3):562-566.
[8]Zhao Y, Zhang Z, Gao Z. A Simple and Workable Moving Objects Segmentation Method [C]//46th International Symposium on Electronics in Marine, 2004. Zadar: IEEE,2004: 585-590.
[9]Hong S,Feng S. A Real--time Algorithm for Moving Objects Detection in Video lmages[C]//Fifth World Congress on Intelligent Control and Automation, WCICA 2004. Hangzhou, 2004 : 4108-4111.
[10]施华 [1],李翠华 [1],韦凤梅 [2],王华伟 [1].基于像素可信度和空间位置的运动目标跟踪[J].计算机研究与发展,2005,42(10):1726-1732.
[11]Cheng Y, Yan H, Hui H. A Novel Algorithm for Pixel--target Detection in Liquid Image[J]. Acta Photonica Sinica, 2002,31 (6): 743-747.
[12]邾继贵[1],叶声华[1].基于近景数字摄影的坐标精密测量关键技术研究[J].计量学报,2005,26(3):207-211.
[13]窦燕[1],孔令富[1].一种基于视觉注意机制的刀具检测方法[J].中国机械工程,2008,19(17):2024-2027.