Email this article The Research of Automatic Registering Detection of Rotary Screen Printing Machine Based on MeanShift and Fast Block-Matching Algorithm
Abstract
With the register detection problem, the color textile image segmentation algorithm based on MeanShift and the block matching algorithm based on Harris corner detection were proposed. The extended MeanShift algorithm was used to segment the textile image, and then different color regions were extracted from the segmented standard image; then the feature points were detected by Harris operator, and with these feature points as the centers, the standard matching blocks were selected; finally the best matching block in the dealt target image were found to calculate register errors. The experiment results show that MeanShift algorithm is not sensitive to the texture of the fabric image, so the algorithm is good for the segmentation of it. And the matching accuracy and speed are improved, because the feature block-matching algorithm combines the point pattern matching with the feature matching algorithm. The research in this paper will lay the foundation for the closed-loop control of online register detection.
Keywords
References
[1] LiPeng,Hao Kuangrong, and Ding Yongsheng,“Fast matching algorithm and its application to rotary screen printing machines,” Journal of Textile Research, vol.29(7), pp. 112-116, July, 2008.
[2] Wang Gang, and Jing Junfeng, “Research of rotary screen printing machine automatic detection system based on machine vision,” Progress in Textile Science & Technology, vol. 4, pp. 43-44, 2009.
[3] Li Yong, Zhou Ying, Shang Huichao, and OuYang Chengzi, “Automatic gray inspection technology based on machine vision,” Journal of Textile Research,vol.28 (8), pp. 124-128, 2009.
[4] Hyung J. Kim, Jong S. Kim,Jung H. Lim, and You Huh, “Detection of wrapping defects by a machine vision and its application to evaluate the wrapping quality of the ring core spun yarn,”Textile Research Journal, vol.79, 17, pp.1616-1624,2009.
http://dx.doi.org/10.1177/0040517509103509
[5] Xin Binjie, Hu Jinlian,and George Baciu, “Visualization of textile surface roughness based on silhouette image analysis,” Textile Research Journal, vol.80, 2, pp.166-176, 2010.
http://dx.doi.org/10.1177/0040517508093779
[6] Huang Chaoli, and Qiu Jianxi, “Research of rotary screen printing machine automatism patterning system based on machine vision,” Progress in Textile Science & Technology, vol.3,pp.48-50,2008.
[7] LiPengfei,Zhanglei,and LiPeng, “The image processing erithmetic of registration inspecting system for plat screen printing machine based on DM642,” Jouranl of Xi'an Polytechnic University, vol.20(5), pp.607-610,2009.
[8] Cheng Yizong, “MeanShift mode seeking and clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17(8), pp.790-799, 1995.
http://dx.doi.org/10.1109/34.400568
[9] H.Mollahosseini, “Detection of color displacement in fabric printing through image analysis,”Journal of the Textile Institute, vol.97:4, pp.333—340.
[10] Fukunaga K,and Hostetler LD, “The estimation of the gradient of adensity function with applications in pattern recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, pp.32-40, 1975.
[11] Harris C, and Satephens MJ, “A combined corner and edge detector,” Image Vision Computting, vol.6(1), pp.121-128, 1988.
[12] Dou Xiaochun, FengYan, and Zhao Xinbo, “A Fast Block-matching Motion Estimation Algorithm,” Journal of Image and Graphics, vol.11, pp.938-942, 2008.
[13] Peng Li, Kuangrong Hao, Yongsheng Ding “Fast Matching Algorithm and its Application to Rotary Screen Printing Machines,” Journal of Textile Research, vol.29(7), pp.112-116, 2009.
[14] Cheung C H, and Po L M, “A novel cross2diamond search algorithm for fast block motion estimation,” IEEE Trans Circuits and Systems For Video Technology, vol.12(12), pp.1168-1177, 2002,
http://dx.doi.org/10.1109/TCSVT.2002.806815
[15] Tavanai H, Palhang M,and Hosseini S A, “Detection of color displacement in fabric printing through image analysis,” Journal of the Textile Institute, vol.97(4), pp. 333-339, 2006.
http://dx.doi.org/10.1533/joti.2005.0148
Full Text: PDF