This web page gives an overview of the image analysis research conducted at HIOF. Traditional image analysis employed a formal approach to the problem, but today it is common to incorporate machine learning techniques to improve the performance.
Our research is focused on employing state-of-the-art machine learning techniques to improve on existing image analysis algorithms. See the links in the menu on the left for more information.
- Improving Graph-based Image Segmentation Using Automatic Programming Published at EvoIASP 2014.
- Edge Pixel Classification Using Automatic Programming Published at NIK 2014.
- Improving the Canny Edge Detector Using Automatic Programming: Improving Non-Max Suppression Accepted to GECCO 2016.