Figure-ground segmentation is an important image processing task that genetic programming (GP) has been successfully introduced to solve. However, existing GP methods use a homogeneous mixture of preprocessing and postprocessing operators for segmentation. This can result in inappropriate operators being connected, leading to poor performance and unnecessary operations in solutions. To address this issue, two new methods are designed to enable GP to conduct image preprocessing, binarisation and postprocessing separately. Specifically, the two methods introduce a strongly-typed representation (StronglyGP) and a two-stage evolution (TwostageGP) in GP respectively Results show that StronglyGP can evolve effective segmentors for the given complex segmentation tasks. However, TwostageGP currently performs poorly, which is likely caused by overfitting, which will be addressed in future work.
[1]
John R. Koza,et al.
Genetic programming - on the programming of computers by means of natural selection
,
1993,
Complex adaptive systems.
[2]
Rabab Kreidieh Ward,et al.
Genetic programming based image segmentation with applications to biomedical object detection
,
2009,
GECCO.
[3]
Luc Van Gool,et al.
The Pascal Visual Object Classes Challenge: A Retrospective
,
2014,
International Journal of Computer Vision.
[4]
Shimon Ullman,et al.
Combined Top-Down/Bottom-Up Segmentation
,
2008,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[5]
Mark E. Roberts,et al.
The Effectiveness of Cost Based Subtree Caching Mechanisms in Typed Genetic Programming for Image Segmentation
,
2003,
EvoWorkshops.