Color Object Recognition based on Spatial Relations between Image Layers

Michaël Clément, Mickaël Garnier, Camille Kurtz, Laurent Wendling

2015

Abstract

The recognition of complex objects from color images is a challenging task, which is considered as a keystep in image analysis. Classical methods usually rely on structural or statistical descriptions of the object content, summarizing different image features such as outer contour, inner structure, or texture and color effects. Recently, a descriptor relying on the spatial relations between regions structuring the objects has been proposed for gray-level images. It integrates in a single homogeneous representation both shape information and relative spatial information about image layers. In this paper, we introduce an extension of this descriptor for color images. Our first contribution is to consider a segmentation algorithm coupled to a clustering strategy to extract the potentially disconnected color layers from the images. Our second contribution relies on the proposition of new strategies for the comparison of these descriptors, based on structural layers alignments and shape matching. This extension enables to recognize structured objects extracted from color images. Results obtained on two datasets of color images suggest that our method is efficient to recognize complex objects where the spatial organization is a discriminative feature.

References

  1. Andreopoulos, A. and Tsotsos, J. K. (2013). 50 Years of object recognition: Directions forward. Comput. Vis. Image Und., 117(8):827-891.
  2. Bloch, I. (2005). Fuzzy spatial relationships for image processing and interpretation: A review. Image Vision Comput., 23(2):89-110.
  3. Bloch, I. and Ralescu, A. L. (2003). Directional relative position between objects in image processing: A comparison between fuzzy approaches. Pattern Recogn., 36(7):1563-1582.
  4. Bosch, A., Zisserman, A., and Muoz, X. (2006). Scene classification via pLSA. In Proc. of ECCV 2006, volume 3954 of LNCS, pages 517-530.
  5. Comaniciu, D. and Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619.
  6. Delaye, A. and Anquetil, E. (2011). Fuzzy relative positioning templates for symbol recognition. In Proc. of IEEE ICDAR 2011, pages 1220-1224.
  7. Egenhofer, M. J. (1989). A formal definition of binary topological relationships. In Foundations of Data Organization and Algorithms, volume 367 of LNCS, pages 457-472.
  8. Garnier, M., Hurtut, T., and Wendling, L. (2012). Object description based on spatial relations between levelsets. In Proc. of IEEE DICTA 2012, pages 1-7.
  9. Inglada, J. and Michel, J. (2009). Qualitative spatial reasoning for high-resolution remote sensing image analysis. IEEE Trans. Geosci. Remote Sens., 47(2):599-612.
  10. Matsakis, P. and Wendling, L. (1999). A new way to represent the relative position between areal objects. IEEE Trans. Pattern Anal. Mach. Intell., 21(7):634-643.
  11. Morales-González, A. and García-Reyes, E. (2013). Simple object recognition based on spatial relations and visual features represented using irregular pyramids. Multimed. Tools Appl., 63(3):875-897.
  12. Santosh, K., Lamiroy, B., and Wendling, L. (2012). Symbol recognition using spatial relations. Pattern Recogn. Lett., 33(3):331-341.
  13. Zhang, D. and Lu, G. (2002). Shape-based image retrieval using Generic Fourier Descriptor. Signal Process. Image, 17(10):825-848.
Download


Paper Citation


in Harvard Style

Clément M., Garnier M., Kurtz C. and Wendling L. (2015). Color Object Recognition based on Spatial Relations between Image Layers . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 427-434. DOI: 10.5220/0005291304270434


in Bibtex Style

@conference{visapp15,
author={Michaël Clément and Mickaël Garnier and Camille Kurtz and Laurent Wendling},
title={Color Object Recognition based on Spatial Relations between Image Layers},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={427-434},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005291304270434},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Color Object Recognition based on Spatial Relations between Image Layers
SN - 978-989-758-089-5
AU - Clément M.
AU - Garnier M.
AU - Kurtz C.
AU - Wendling L.
PY - 2015
SP - 427
EP - 434
DO - 10.5220/0005291304270434