Dr. Vedang Chauhan

Image currently not available!

Machine Vision and Learning for Inspection


Continuous operations of automated assembly machines have potential for faults with subsequent machine downtime. Early fault detection and preventive maintenance can reduce the amount of downtime and increase the production. Traditional fault detection methods check for deviations from fixed threshold limits with multiple mechanical, optical and proximity sensors. The topics of this address is the development of a machine vision inspection (MVI) system to detect and classify multiple faults using a single camera as a sensor. This presentation will speak regarding machine vision inspection developed with machine leaning to improve the quality of product and reduce the machine downtime. An industrial automated O-ring assembly machine that places O-rings on to continuously moving plastic carriers at a rate of over 100 assemblies per minute was used for the research. An industrial CCD camera with LED panel lights for illumination was used to acquire videos of the machine’s operation. A Programmable Logic Controller (PLC) with a Human- Machine Interface (HMI) allowed for the generation of faults in a controlled fashion. Three MVI methods were developed for this application were based on based on Gaussian Mixture Models (GMMs), optical flow and morphological image processing. The performance was measured and compared for the three methods. The idea of MVI for automated machine was extended and applied to coin classification problem using deep learning techniques. Latest applications and research ideas in the area of machine vision, machine learning and deep learning will be discussed in the keynote address.


Dr. Vedang Chauhan is a faculty member in Mechanical Engineering Department at Western New England University in Massachusetts, USA. He has received PhD in Mechanical Engineering with specialization in machine vision and mechatronics from Queen’s University in Canada. He has 15 years of teaching and research experience and has worked on numerous industrial research projects. He is a very active researcher and his research interests are design and development of machine vision and machine learning applied to industrial automation. He has published research articles in various conferences and journals and acted as a reviewer for machine vision and machine learning journals.