The automated inspection and sorting of parts is a common application of Machine Vision. The sorting of parts is possible only after reliable classification. Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) are popular choices as classification algorithms. Classifiers developed from supervised algorithms perform well when trained for a specific application with known classes. Their drawback is that they are considered inflexible as they cannot be easily applied to a different application without extensive retuning. Moreover, for a given application, they do not perform properly if there are unknown classes. Classifiers developed from semi-unsupervised algorithms can work with unknown classes but cannot work with multiple known classes. The above problem can be addressed by a hybrid two-layered approach for the classifier with a combination of supervised SVMs, semi-unsupervised SVMs and supervised ANNs. An introduction to the software package known as FlexMVS for Flexible Machine Vision System will be given that can evaluate the above hybrid approach.
About the Speaker: Dr. Keyur D. Joshi is a researcher, teacher and learner in the fields relating with mechatronics engineering. He recently completed his PhD in Mechanical Engineering from Queen’s University at Kingston, Canada with the sub-area of machine vision. He was a teaching assistant at the university and taught mechatronics, instrumentation and control system related concepts. He has several publications on topics such as mechatronics, machine vision and digital image processing. His current research interests are machine vision, computer vision, fuzzy logic, deep machine learning and artificial intelligence.