On a high-speed production line, tilt of bottles, burrs on the bottleneck, and residual droplets after
cleaning affect accuracy of PET bottle inspection. To deal with the problem, a bottle detection algorithm
based on symmetry matching is proposed. Considering symmetry of the bottle image, the bottle axis can
be determined accurately by registering the images before and after horizontal flipping. Thus tilts can be
compensated. Burrs and droplets are eliminated by using correlation of pixels on both sides of the axis.
Consequently, the support rings can be detected and bottle caps can be classified precisely. Experimental
results show high accuracy, speed and robustness of the proposed algorithm as compared with the state-of-theart
techniques. For images sized 640×480, the average detection time is 27.4 ms, which meets the requirement
of high-speed production lines.
WANG Gui-jin1, LIU Bo1, HE Bei1, ZHANG Shu-jun2, MENG Long2
. Real-Time PET Cap Defect Inspection Based on Symmetry Match[J]. Journal of Applied Sciences, 2014
, 32(6)
: 617
-624
.
DOI: 10.3969/j.issn.0255-8297.2014.06.011
[1] MALAMAS E N, PETRAKIS E G M, ZERVAKIS M, PETIT L, LEGAT J D. A survey on industrial vision systems, applications and tools[J]. Image and Vision Computing, 2003, 21(2): 171-188.
[2] DUAN F, WANG Y, LIU H, LI Y. A machine vision inspector for beer bottle [J]. Engineering Applications of Artificial Intelligence, 2007, 20(7): 1013-1021.
[3] 孙怀远, 周夫之, 陆尚卿.机器视觉技术在药液灌装量检测中的应用[J].计算机应用与软件，2009, 6: 247-248.
SUN Huaiyuan, ZHOU Fuzhi, LU Shangqing. Applying machine vision technology in filling quantity detection of liquid medicine[J]. Computer Applications and Software, 2009, 6: 247-248. (in Chinese)
[4] LIU H, WANG Y, DUAN F. An empty bottle intelligent inspector based on support vector machines and fuzzy theory[C]. Conference Proceedings of Sixth World Congress on Intelligent Control and Automation. 2006: 9739-9743.
[5] 邹振兴，谢云，林奇鸿，陈炳成. 基于SOPC技术的PET瓶缺陷检测系统设计[J]. 现代电子技术，2009, 10: 58-61.
ZOU Zhenxing, XIE Yun, LIN Qihong, CHEN Bingcheng. Design of PET bottle defect detection system based on SOPC[J]. Modern Electronics Technique, 2009, 10: 58-61. (in Chinese)
[6] YAZDI L, PRABUWONO A S, GOLKAR E. Feature extraction algorithm for fill level and cap inspection in bottling machine[C]. International Conference on Pattern Analysis and Intelligent Robotics, 2011, 1: 47-52.
[7] 郑云峰，王贵锦，何贝，李艳丽，林行刚. 基于直线拟合算法的PET瓶瓶盖检测方法[J]. 计算机应用研究，2011, 28(11): 4398-4400.
ZHENG Yunfeng, WANG Guijin, HE Bei, LI Yanli, LIN Xinggang. PET bottle cap inspection method based on linear fitting algorithm[J]. Application Research of Computers, 2011, 28(11): 4398-4400. (in Chinese)
[8] 张树君，陈大千，辛莹莹，国磊，姜辉. 基于图像的 PET 瓶瓶盖和液位的检测设备[J]. 轻工机械，2013 (2): 71-73.
ZHANG Shujun, CHEN Daqian, XIN Yingying, GUO Lei, JIANG Hui. Detection device of PET bottle and liquid based on image[J]. Light Industry Machinery, 2013, 31(2): 71-74. (in Chinese)
[9] 郑海成，谢云. PET 瓶封盖质量在线检测系统的设计与实现[J]. 电子技术应用，2012, 38(8): 20-22.
ZHENG Haicheng, XIE Yun. Design and implementation of PET bottle package defect detection system based on dual core processor [J]. Application of Electronic Technique, 2012, 38(8): 20-22. (in Chinese)
[10] CARRASCO M, PIZARRO L, MERY D. Image acquisition and automated inspection of wine bottlenecks by tracking in multiple views[C]//Iscgav'08: Proceedings of the 8th Wseas International Conference on Signal Processing, Computational Geometry and Artificial Vision, 2008: 84-89, 235.
[11] NG HF. Automatic thresholding for defect detection[J]. Pattern Recognition Letters, 2006, 27(14): 1644-1649.
[12] 章品正，王健宏. 一种应用机器学习的车牌定位方法[J]. 应用科学学报，2011, 29(2): 147-152.
ZHANG Pinzheng, WANG Jianhong. Vehicle license plate location based on machine learning[J]. Journal of Applied Sciences, 2011, 29(2): 147-152. (in Chinese)
[13] TZIMIROPOULOS G, ARGYRIOU V, STATHAKI T. Symmetry detection using frequency domain motion estimation techniques [C]//International Conference on Acoustics, Speech, and Signal Processing, 2008: 861-864.
[14] KELLER Y, SHKOLNISKY Y. A signal processing approach to symmetry detection [J]. IEEE Transaction on Image Processing, 2006, 15(8): 2198-2207.
[15] LOY G, EKLUNDH J O. Detecting symmetry and symmetric constellations of features[C]//European Conference on Computer Vision, 2006: 508-521.
[16] CHO M, LEE K M. Bilateral symmetry detection via symmetry-growing [C]//Proceedings of the British Machine Vision Conference, 2009: 1-8.
[17] HE Bei, WANG Guijin, YIN Xuanwu, LIU Bo, LIN Xinggang. Self-clustering symmetry detection [J]. IEICE Transactions on Information and Systems, 2012, 95(9): 2359-2362.
[18] HAUAGGE D C, SNAVELY N. Image matching using local symmetry features [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012: 206-213.
[19] ZITOVA B, FLUSSER J. Image registration methods: a survey [J]. Image and Vision Computing, 2003, 21(11): 977-1000.
[20] BAKER S, MATTHEWS I. Lucas-Kanade 20 years on: A unifying framework [J]. International Journal of Computer Vision, 2004, 56(3): 221-255.
