Jimi Shanahan, Barry Thomas, Majid Mirmehdi, Neill Campbell, Trevor Martin, James Baldwin
Proceedings of British Machine Vision Conference (BMVC)1999, Nottingham, UK
Current learning approaches to computer vision have mainly focussed on low-level image processing and
object recognition, while tending to ignore higher level process-ing for understanding. We propose an approach
to scene analysis that facilitates the transition from recognition to understanding. It begins by segmenting the
image into regions using standard approaches, which are then classified using a discovered fuzzy Cartesian
granule feature classifier. Understanding is made possible through the trans-parent and succinct nature of the
discovered models. The recognition of roads in images is taken as an illustrative problem. The discovered
fuzzy models while providing high levels of accuracy (97%), also provide understanding of the problem domain
through the transparency of the learnt models. The learning step in the proposed approach is compared with
other techniques such as decision trees, naïve Bayes and neural net-works using a variety of performance
criteria such as accuracy, understandability and efficiency.
Report number: