Abstract
Finding correspondence regions between images is fundamental to recovering three dimensional information from multiple frames of the same scene and content based image retrieval. To be good, correspondence regions should be easily found, richly characterised and have a good trade-off between density and uniqueness. Maximally stable extremal regions (MSER’s) are amongst the best known methods to tackle this problem. Here, we present an implementation of the sieve algorithm that not only generates MSER’s but can also generate stable salient contours (SSC’s) in different ways. The sieve decomposes the image according to local grayscale intensities and produces a tree in nearly O(N) where N is the number of pixels. The exact shape of the tree depends on the criteria used to control the merging of extremal regions with less extreme neighbours. We call the resulting data structure a ‘structured image’. Here, a structured image in which MSER’s are embedded is compared with those associated with two types of SSC’s. The correspondence rate generated by each of these methods is compared using the standard evaluation method due to Mikalajczyk and the results show that SSC’s identified using colour and texture moments are generally better than the others.
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
Bangham, J., Hidalgo, J., Harvey, R., Cawley, G.: The segmentation of images via scale-space trees (1998)
Bangham, J.A., Chardaire, P., Ling, P., Pye, C.J.: Multiscale nonlinear decomposition: the sieve decomposition theorem. IEEE Trans. Pattern Analysis and Machine Intelligence 18, 518–527 (1996)
Gibson, S., Harvey, R.: Trecognition and retrieval via histogram trees. In: British Machine Vision Conference, vol. 2, pp. 531–540 (2001)
Koenderink, J.J.: The structure of images. Biological Cybernetics 50, 363 (1984)
Lan, Y., Harvey, R., Perez-Torres, R.: Finding stable salient contours. In: Proceedings of the British Machine Vision Conference, Oxford (2005)
Bretzner, L., Lindeberg, T.: On the handling of spatial and temporal scales in feature tracking. In: Proc. First Int. Conf. on Scale-space theory, pp. 128–139. Springer, Heidelberg (1997)
Lowe, D.: Sift: Distinctive image features from scale invariant keypoints. In: Proceedings of IJCV, vol. 1, pp. 91–110 (2004)
Matas, J., Chum, O., Martin, U., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proceedings of the British Machine Vision Conference, London, vol. 1, pp. 384–393 (2002)
Tuytelaars, T., Schmid, C., Zisser-Man, A., Matas, J., Schaffalitzky, F., Kadir, T., Mikolajczyk, K., van Gool, L.: A comparison of affine region detectors. International Journal of Computer Vision, 43–72 (2005)
Harvey Moravec, R., Bangham, J.A.: Scale trees for stereo vision. IEE Proceedings: Vision, Image and Signal Processing 147(4), 363–370 (2000)
Bosson, A., Harvey, R., Bangham, J.A.: Robustness of some scale-spaces. In: British Machine Vision Conference (BMVC 1997), Colchester, UK, vol. 1, pp. 11–20 (1997)
Southam, P.: Texture granularities. In: International Conference on Image Analysis and Processing, Italy, vol. 1, pp. 233–240 (2005)
Witkin, A.P.: Scale-space filtering. In: 8th International Joint Conference on Artificial Intelligence, pp. 1019–1022 (1983)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pastrana Palma, A., Bangham, J.A. (2007). Correspondence Regions and Structured Images. In: Gelbukh, A., Kuri Morales, Á.F. (eds) MICAI 2007: Advances in Artificial Intelligence. MICAI 2007. Lecture Notes in Computer Science(), vol 4827. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76631-5_55
Download citation
DOI: https://doi.org/10.1007/978-3-540-76631-5_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76630-8
Online ISBN: 978-3-540-76631-5
eBook Packages: Computer ScienceComputer Science (R0)