Abstract
This paper presents a bottom-up approach for perceptual segmentation of natural images. The segmentation algorithm consists of two consecutive stages: firstly, the input image is partitioned into a set of blobs of uniform colour (pre-segmentation stage) and then, using a more complex distance which integrates edge and region descriptors, these blobs are hierarchically merged (perceptual grouping). Both stages are addressed using the Combinatorial Pyramid, a hierarchical structure which can correctly encode relationships among image regions at upper levels. Thus, unlike other methods, the topology of the image is preserved. The performance of the proposed approach has been initially evaluated with respect to ground-truth segmentation data using the Berkeley Segmentation Dataset and Benchmark. Although additional descriptors must be added to deal with textured surfaces, experimental results reveal that the proposed perceptual grouping provides satisfactory scores.
Chapter PDF
References
Arbeláez, P.: Boundary extraction in natural images using ultrametric contour maps. In: Proc. 5th IEEE Workshop Perceptual Org. in Computer Vision, pp. 182–189 (2006)
Arbeláez, P., Cohen, L.: A metric approach to vector-valued image segmentation. Int. Journal of Computer Vision 69, 119–126 (2006)
Bister, M., Cornelis, J., Rosenfeld, A.: A critical view of pyramid segmentation algorithms. Pattern Recongition Letters 11(9), 605–617 (1990)
Borůvka, O.: O jistém problému minimálnim. Práce Mor. Pr̆írodvĕd. Spol. v Brnĕ (Acta Societ. Scienc. Natur. Moravicae) 3(3), 37–58 (1926)
Brun, L., Kropatsch, W.: Introduction to combinatorial pyramids. In: Bertrand, G., Imiya, A., Klette, R. (eds.) Digital and Image Geometry. LNCS, vol. 2243, pp. 108–128. Springer, Heidelberg (2002)
Haxhimusa, Y., Ion, A., Kropatsch, W.G.: Evaluating hierarchical graph-based segmentation. In: Tang, Y.Y., et al. (eds.) Proceedings of 18th International Conference on Pattern Recognition (ICPR), Hong Kong, China, vol. 2, pp. 195–198. IEEE Computer Society, Los Alamitos (2006)
Haxhimusa, Y., Kropatsch, W.G.: Segmentation graph hierarchies. In: Fred, A., Caelli, T.M., Duin, R.P.W., Campilho, A.C., de Ridder, D. (eds.) SSPR&SPR 2004. LNCS, vol. 3138, pp. 343–351. Springer, Heidelberg (2004)
Huart, J., Bertolino, P.: Similarity-based and perception-based image segmentation. In: Proc. IEEE Int. Conf. on Image Processing, vol. 3, pp. 1148–1151 (2005)
Kropatsch, W.: Building irregular pyramids by dual graph contraction. IEEE Proc. Vision, Image and Signal Processing 142(6), 366–374 (1995)
Lau, H., Levine, M.: Finding a small number of regions in an image using low-level features. Pattern Recognition 35, 2323–2339 (2002)
Marfil, R., Bandera, A.: Comparison of perceptual grouping criteria within an integrated hierarchical framework. In: Torsello, A., Escolano, F., Brun, L. (eds.) GbRPR 2009. LNCS, vol. 5534, pp. 366–375. Springer, Heidelberg (2009)
Marfil, R., Molina-Tanco, L., Bandera, A., Rodríguez, J.A., Sandoval Hernández, F.: Pyramid segmentation algorithms revisited. Pattern Recognition 39(8), 1430–1451 (2006)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using brightness, color, and texture cues. IEEE Trans. on Pattern Analysis Machine Intell. 26(1), 1–20 (2004)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. Int. Conf. Computer Vision (2001)
Pham, T., Smeulders, A.: Learning spatial relations in object recognition. Pattern Recognition Letters 27, 1673–1684 (2006)
Zlatoff, N., Tellez, B., Baskurt, A.: Combining local belief from low-level primitives for perceptual grouping. Pattern Recognition 41, 1215–1229 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Antúnez, E., Marfil, R., Bandera, A. (2011). A New Perception-Based Segmentation Approach Using Combinatorial Pyramids. In: Maino, G., Foresti, G.L. (eds) Image Analysis and Processing – ICIAP 2011. ICIAP 2011. Lecture Notes in Computer Science, vol 6978. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24085-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-24085-0_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24084-3
Online ISBN: 978-3-642-24085-0
eBook Packages: Computer ScienceComputer Science (R0)