Abstract
Figure-ground segmentation is a process of separating regions of interest from unimportant backgrounds. It is challenging to separate objects from target images with high variations (e.g. cluttered backgrounds), which requires effective feature sets to capture the discriminative information between object and background regions. Feature construction is a process of transforming a given set of features to a new set of high-level features, which considers the interactions between the previous features, thus the constructed features can be more meaningful and effective. As Genetic programming (GP) is a well-suited algorithm for feature construction (FC), it is employed to conduct both multiple FC (MFC) and single FC (SFC), which aims to improve the segmentation performance for the first time in this paper. The cooperative coevolution technique is introduced in GP to construct multiple features from different types of image features separately while conducting feature combination simultaneously, called as CoevoGPMFC. One wrapper method (wrapperGPSFC) is also designed, and one well-performing embedded method (embeddedGPSFC) is introduced as a reference method. Compared with the original features extracted by existing feature descriptors, the constructed features from the proposed methods are more robust and performance better on the test set. Moreover, the features constructed by the three methods achieve similar performance for the given segmentation tasks.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Borenstein, E., Ullman, S.: Combined top-down/bottom-up segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2109–2125 (2008)
Cano, A., Ventura, S., Cios, K.J.: Multi-objective genetic programming for feature extraction and data visualization. Soft Comput. 1–21 (2015). doi:10.1007/s00500-015-1907-y
Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98–136 (2014)
Koza, J.R.: Genetic Programming: on the Programming of Computers by Means of Natural Selection, vol. 1. MIT Press, Cambridge (1992)
Krawiec, K., Bhanu, B.: Coevolution and linear genetic programming for visual learning. In: Cantú-Paz, E., et al. (eds.) GECCO 2003. LNCS, vol. 2723, pp. 332–343. Springer, Heidelberg (2003). doi:10.1007/3-540-45105-6_39
Kumar, M.P., Koller, D.: Efficiently selecting regions for scene understanding. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3217–3224. IEEE (2010)
Lee, Y.J., Grauman, K.: Object-graphs for context-aware visual category discovery. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 346–358 (2012)
Liang, Y., Zhang, M., Browne, W.N.: Feature construction using genetic programming for figure-ground image segmentation. In: Leu, G., Singh, H.K., Elsayed, S. (eds.) Intelligent and Evolutionary Systems. PALO, vol. 8, pp. 237–250. Springer, Heidelberg (2017). doi:10.1007/978-3-319-49049-6_17
Neshatian, K.: Feature manipulation with genetic programming (2010)
Neshatian, K., Zhang, M., Andreae, P.: A filter approach to multiple feature construction for symbolic learning classifiers using genetic programming. IEEE Trans. Evol. Comput. 16(5), 645–661 (2012)
Poli, R.: Genetic programming for image analysis. In: Proceedings of the 1st Annual Conference on Genetic Programming, pp. 363–368. MIT Press (1996)
Roth, V., Lange, T.: Adaptive feature selection in image segmentation. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 9–17. Springer, Heidelberg (2004). doi:10.1007/978-3-540-28649-3_2
Sondhi, P.: Feature construction methods: a survey. sifaka. cs. uiuc. edu, 69, 70–71 (2009)
Zou, W., Bai, C., Kpalma, K., Ronsin, J.: Online glocal transfer for automatic figure-ground segmentation. IEEE Trans. Image Process. 23(5), 2109–2121 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Liang, Y., Zhang, M., Browne, W.N. (2017). Wrapper Feature Construction for Figure-Ground Image Segmentation Using Genetic Programming. In: Wagner, M., Li, X., Hendtlass, T. (eds) Artificial Life and Computational Intelligence. ACALCI 2017. Lecture Notes in Computer Science(), vol 10142. Springer, Cham. https://doi.org/10.1007/978-3-319-51691-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-51691-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-51690-5
Online ISBN: 978-3-319-51691-2
eBook Packages: Computer ScienceComputer Science (R0)