Object recognition in industrial environments using support vector machines and artificial neural networks
- First Online:
- Cite this article as:
- Barry, T.J. & Nagarajah, C.R. Int J Adv Manuf Technol (2010) 48: 815. doi:10.1007/s00170-009-2313-3
- 119 Downloads
This paper presents a comparison between Artificial Neural Networks and Support Vector Machines in the application of classifying automotive wheels in an industrial environment. Performance of these two approaches over a range of classifier parameters on a data set pre-processed in multiple ways has been evaluated and the results analysed. Results indicate that the best performance is obtained using a support vector machine approach incorporating a linear kernel.