Study on the method of adhesive parts particle counting based on HALCON

Huang Mingxin

Анотація


In order to solve the problem of low efficiency and low accuracy in the traditional adhesive parts particle counting method, it is proposed to implement an improved watershed segmentation algorithm by means of the HALCON image processing technology based on the Euclidean distance transform and the Gaussian filter. First of all, the parts particle image is obtained with the help of an industrial camera. Then the image undergoes pre-processing. Afterwards, the image is subject to mathematical morphology processing. The last step is application of the improved watershed segmentation algorithm. The experimental results show that the algorithm can segment the adhesive parts particles effectively, providing a guarantee for an accurate count of the parts particles.


Ключові слова


adhesion; HALCON; distance transformation; Gaussian filter; watershed segmentation

Повний текст:

PDF (English)

Посилання


Zhang Yujin. Image engineering: volume one image processing [M]. Beijing, Tsinghua University Press, 2006:1-3.

Steger C., Ulrich M., Wieldemmann C. Machine vision algorithms and applications [M]. Germany, Wiley-Vch, 2007.

Xu Wei Qin. Research on image analysis technique of adhesive particles based on watershed segmentation [D]. CHANGSHA, Central South University, 2011.

Noble J. A. From inspection to process understanding and monitoring: a view on computer vision in manufacturing [J]. Image and Vision Computing, 1995, 13(3):197-214.

Weszka J. S., Rosenfeld A. Histogram modification for threshold selection [J]. IEEE SMC, 1999, 9(2):28-37.

Ni Zhiqiang, Ye Ming. Method of the segmentation of touching image based on watershed transform [J]. Computer System Applications, 2014, 23(6):93-97.

Wang Wencheng. Design of gear defect detection system based on the Halcon [J]. Journal of Mechanical Transmission, 2014, 38(9):60-63.

Jin Can, Research on printing image quality detection technology based on HALCON [D]. CHANGSHA, Central South University, 2013.

Borgefors G. Distance transformations in digital images [J]. Computer Vision, 1986, 34(3):344-371.

Jin Bei. The design of machine vision teaching experiment system based on HALCON [D]. Beijing, Beijing Jiaotong University, 2012.

Sun Huaiyuan, Liao Yuehua, Zhou Fu-zhi, et al. Study on the batch detection technology of pharmaceutical bottles based on HALCON [D]. Shanghai, University of Shanghai for Science and Technology, 2008.

Bianconi F., Ceccarelli L., Fernández A., et al. A sequential machine vision procedure for assessing paper impurities [J]. Computers in Industry, 2013, 65 (2):325-332.




DOI: https://doi.org/10.15589/SMI20170211