ABSTRACT
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.
- Eran Borenstein and Shimon Ullman. 2008. Combined top-down/bottom-up segmentation. Pattern Analysis and Machine Intelligence, IEEE Transactions on 30, 12 (2008), 2109--2125. Google ScholarDigital Library
- Mark Everingham, SM Ali Eslami, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2014. The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision 111, 1 (2014), 98--136. Google ScholarDigital Library
- John Koza. 1992. Genetic Programming: On the Programming of Computers by Natural Selection. MIT Press, Cambridge, CA. Google ScholarDigital Library
- Mark E Roberts. 2003. The effectiveness of cost based subtree caching mechanisms in typed genetic programming for image segmentation. In Workshops on Applications of Evolutionary Computation. Springer, 444--454. Google ScholarDigital Library
- Yutaka Sasaki. 2007. The truth of the F-measure. Teach Tutor mater (2007), 1--5.Google Scholar
- Tarundeep Singh, Nawwaf Kharma, Mohmmad Daoud, and Rabab Ward. 2009. Genetic programming based image segmentation with applications to biomedical object detection. In Proceedings of the 11th Annual conference on Genetic and evolutionary computation. ACM, 1123--1130. Google ScholarDigital Library
Index Terms
- Learning figure-ground image segmentors by genetic programming
Recommendations
Multi-objective Genetic Programming for Figure-Ground Image Segmentation
Proceedings of the Second Australasian Conference on Artificial Life and Computational Intelligence - Volume 9592Figure-ground segmentation is a crucial preprocessing step in areas of computer vision and image processing. As an evolutionary computation technique, genetic programming GP can evolve algorithms automatically for complex problems and has been ...
Image feature selection using genetic programming for figure-ground segmentation
Figure-ground segmentation is the process of separating regions of interest from unimportant background. One challenge is to segment images with high variations (e.g. containing a cluttered background), which requires effective feature sets to capture ...
Figure-ground image segmentation using feature-based multi-objective genetic programming techniques
AbstractFigure-ground image segmentation is a process of separating regions of interest from a target image. Genetic programming has been employed to evolve segmentors that have the potential to capture high variations of images and conduct accurate ...
Comments