Special shaped softgel inspection system based on machine vision

A machine vision system for special shaped softgel inspection is proposed in this paper, which is composed of a pair of CMOS cameras and a diffuse blue illuminator. Because the flaws appear in softgel shells edge is difficult to detect, these two cameras are arranged symmetrically upon softgels with a certain angle to avoid blind area. An image segment method combined automatic threshold and edge detection is proposed to extract the outer contour of softgels. The internal flaws can be detected by dynamic threshold and morphological feature analysis. The experiments shows that the flaws in fish oil softgels such as missing pill, excess pill, abnormal pill, bubbles, black spots and rubber defects can be detected successfully, and the encapsulating line is distinguished from those defects. The resolution of detection is smaller than 0.1mm and the detection accuracy is about 99.9%.

[1]  Markus Ulrich,et al.  Machine Vision Algorithms and Applications , 2007 .

[2]  Jiewen Zhao,et al.  Machine Vision on-Line Detection Quality of Soft Capsules Base on SVM , 2008, CCTA.

[3]  Wei Zhang,et al.  Alnico sheet measurement based on machine vision , 2013, 2013 International Conference on Anti-Counterfeiting, Security and Identification (ASID).

[4]  J. B. Li,et al.  Machine vision technology for detecting the external defects of fruits — a review , 2015 .

[5]  Wang Lei,et al.  Mini Milling Cutter Measurement Based on Machine Vision , 2011 .

[6]  Gang Zhou,et al.  Template match using local feature with view invariance , 2013, Other Conferences.

[7]  Zhu Zhengtao,et al.  Pre-processing Techniques for On-Line Capsule Inspection Based on Machine Vision , 2011, 2011 Fourth International Conference on Intelligent Computation Technology and Automation.