Abstract
In this work a method of object localization on the basis of its expected structure is presented. An active partition approach is used for that purpose where, instead of pixels, line segments are used to represent image content. The expectation about object being sought is expressed in the form of model where the expected line segments are specified explicitly. Both image representation and model take into account relations between segments and thus both can be considered as graphs constituting their structural description. The best subsets of line segments are sought in a systematic search process with properly defined model fit function. It allows to identify a subset of segments that resembles the given model even if the segments are detected imprecisely.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tomczyk, A.: Detection of Line Segments. Journal of Applied Computer Science 22(2), 81–90 (2014)
von Gioi, R.G., Jakubowicz, J., Morel, J.-M., Randall, G.: LSD: a Line Segment Detector. Image Processing On Line 2, 35–55 (2012)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision, 321–331 (1988)
Caselles, V.: Geometric models for active contours. In: Proceedings of the International Conference on Image Processing, pp. 9–12 (1995)
Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape model - their training and application. CVGIP Image Understanding 61(1), 38–59 (1994)
Tomczyk, A., Szczepaniak, P.S.: Adaptive potential active contours. Pattern Analysis and Application 14, 425–440 (2011)
Tomczyk, A., Szczepaniak, P.S., Pryczek, M.: Cognitive hierarchical active partitions in distributed analysis of medical images. Journal of Ambient Intelligence and Humanized Computing 4(3), 357–367 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Jadczyk, M., Tomczyk, A. (2015). Object Localization Using Active Partitions and Structural Description. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2015. Lecture Notes in Computer Science(), vol 9119. Springer, Cham. https://doi.org/10.1007/978-3-319-19324-3_65
Download citation
DOI: https://doi.org/10.1007/978-3-319-19324-3_65
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19323-6
Online ISBN: 978-3-319-19324-3
eBook Packages: Computer ScienceComputer Science (R0)