Multi-camera Vision System for the Inspection of Metal Shafts

To address the needs of the manufacturing industry, the automation of quality inspection processes is often performed. Ensuring the high reliability and accuracy of measurement usually requires the development of specialized systems dedicated for specific applications. In the paper, a multi-camera vision system developed for the automatic inspection of metal shafts in the automotive industry is presented. The novel solution of the inspection system is based on the application of a set of three cameras that allow the inspection of shafts in separated areas. The system enables the detection and recognition of the following features: thread, knurls, grooves, and measurements of the shaft length. The image processing is performed with the use of filtering, morphology operations (dilation and erosion), and edge detection. The two-dimensional Look-up Table has been created in order to calculate a correct shaft length considering perspective errors of lenses.

[1]  Hitoshi Matsushima,et al.  Contour representation of binary images using run-type direction codes , 1997, Machine Vision and Applications.

[2]  Giulio Rosati,et al.  Real-time defect detection on highly reflective curved surfaces , 2009 .

[3]  Dusmanta Kumar Mohanta,et al.  Review of vision-based steel surface inspection systems , 2014, EURASIP Journal on Image and Video Processing.

[4]  Hyungsuck Cho.  Opto-mechatronic systems handbook techniques and applications , 2003 .

[5]  Franz Pernkopf,et al.  Image Acquisition Techniques for Automatic Visual Inspection of Metallic Surfaces , 2003 .

[6]  R. Sitnik,et al.  New concept of fast hybrid contact and no-contact measurement for automotive industry , 2006, SPIE Photonics Europe.

[7]  Xiangyang Hao,et al.  Automatic detection system of shaft part surface defect based on machine vision , 2015, Optical Metrology.

[8]  José R. Perán,et al.  Automated visual classification of frequent defects in flat steel coils , 2011 .

[9]  Qingchang Tan,et al.  Measurement of shaft diameters by machine vision. , 2011, Applied optics.

[10]  Z. Hocenski,et al.  Failure detection and isolation in ceramic tile edges based on contour descriptor analysis , 2007, 2007 Mediterranean Conference on Control & Automation.

[11]  Hong Zheng,et al.  Automatic inspection of metallic surface defects using genetic algorithms , 2002 .

[12]  Jing Liu,et al.  Instrumentation design and precision analysis of the external diameter measurement system based on CCD parallel light projection method , 2009, International Conference on Optical Instruments and Technology.

[13]  Tony Lindeberg.  Edge Detection and Ridge Detection with Automatic Scale Selection , 2004, International Journal of Computer Vision.

[14]  Muhammad Azmi Ayub,et al.  In-line Inspection of Roundness Using Machine Vision , 2014 .

[15]  Euripides G. M. Petrakis,et al.  A survey on industrial vision systems, applications, tools , 2003, Image Vis. Comput..

[16]  Anatoli I. Dashchenko,et al.  Manufacturing Technologies for Machines of the Future , 2003 .

[17]  K. Kannan,et al.  A Roadmap for Designing an Automated Visual Inspection System , 2010 .