Abstract
A novel approach to content-based image retrieval is presented. The method supports recognition of objects under a very wide range of viewing and illumination conditions and is robust to occlusion and background clutter. Starting from robustly detected ’distinguished regions’ of data dependent shape, local affine frames are established by affine-invariant constructions exploiting invariant properties of the second moment matrix and bi-tangent points. Direct comparison of photometrically normalised colour intensities in normalised frames facilitates robust, affine and illumination invariant, but still very selective matching. The potential of the proposed approach is experimentally verified on FOCUS — a publicly available image database — using a standard set of query images. The results obtained are superior to the state of the art. The method operates successfully on images with complex background, where the sought object covers only a fraction (around 2%) of the database image. Examples of precise localisation of the query objects in an image are shown too.
The authors were supported by the EU project IST-2001-32184, the Czech Ministry of Education project MSM 210000012 and a CTU grant No. CTU0209613.
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
Swain, M., Ballard, D.: Color indexing. In: International Journal of Computer Vision, vol. 7, no. 1. (1991) 11–32
Finlayson, G. D., Chatterjee, S. S., Funt, B. V.: Color angular indexing. In: ECCV. (1996) 16–27
Funt, B., Finlayson, G., Color, C.: Color constant color indexing. IEEE Transactions on Pattern Analysis and Machine Intelligence 17 (1995) 522–529
Liu, F., Picard, R. W.: Periodicity, directionality, and randomness: Wold features for image modeling and retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 18 (1996) 7–733
E., Gary, R., Mehrotra: Shape similarity-based retrieval in image database systems. SPIE 1662 (1992) 2–8
Mokhtarian, F., Abbasi, S., Kittler, J.: Robust and efficient shape indexing through curvature scale space. In: In Proceedings of British Machine Vision Conference, Edinburgh, UK. (1996) 53–6
Bimbo, A., Pala, P.: Effective image retrieval using deformable templates. In: ICPR96. (1996) 120–123
Mindru, F., Moons, T., Gool, L. V.: Recognizing color patterns irrespective of viewpoint and illumination. In: CVPR99. (1999) 368–373
Tuytelaars, T., Gool, L. V.: Content-based image retrieval based on local affinely invariant regions. In: Proc. Visual’ 99: Information and Information Systems. (1999) 493–500
Park, K., Yun, I., Lee, S. U.: Color image retrieval using a hybrid graph representation. Journal of Image and Vision Computing 17(7) (1999) 465–474
Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (2000) 1349–1380
Matas, J., Chum, O., Urban, M., Pajdla, T.: Distinguished regions for wide-baseline stereo. Research Report CTU—CMP-2001-33, Center for Machine Perception, K333 FEE Czech Technical University, Prague, Czech Republic (2001) ftp://cmp.felk.cvut.cz/pub/cmp/articles/matas/matas-tr-2001-33.ps.gz.
Suk, T., Flusser, J.: Convex layers: A new tool for recognition of projectively deformed point sets. In Solina, F., Leonardis, A., eds.: Computer Analysis of Images and Patterns: 8th International Conference CAIP’99. Number 1689 in Lecture Notes in Computer Science, Berlin, Germany, Springer (1999) 454–461
Mundy, J. L., Zisserman, A., eds.: Geometric Invariance in Computer Vision. The MIT Press (1992)
Cohen, S.: Finding color and shape patterns in images. Technical Report STAN-CS-TR-99-1620, Stanford University (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Obdržálek, Š., Matas, J. (2002). Local Affine Frames for Image Retrieval. In: Lew, M.S., Sebe, N., Eakins, J.P. (eds) Image and Video Retrieval. CIVR 2002. Lecture Notes in Computer Science, vol 2383. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45479-9_34
Download citation
DOI: https://doi.org/10.1007/3-540-45479-9_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43899-1
Online ISBN: 978-3-540-45479-3
eBook Packages: Springer Book Archive