Abstract
An accurate calculation of the size distribution of coarse particles is crucial in the mining and quarrying industry. Machine vision has the capability to overcome many inherent limitations of traditional sieving methods and is an active research area. However, inaccurate image segmentation of particles through software based algorithms is a significant source of error. In this paper, a hardware based approach to improving image segmentation is demonstrated using multi-flash Imaging (MFI), where multiple images captured with different illumination allows depth edges around a particle to be captured through shadow information. The MFI method is compared with conventional segmentation methods such as watershed and Canny edge detection. In order to provide more accurate evaluation of performance wooden spheres of known diameter were evaluated. Imaging the size distribution of pebbles provided a practical scenario in the evaluation of MFI. The results revealed that MFI produced more accurate size estimations than conventional segmentation techniques for both the wooden spheres and pebbles, demonstrating the potential for future use in the mining industry.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
