Abstract
This paper presents an efficient method for finding salient differential features in images. We argue that the problem of finding salient features among all the possible ones is equivalent to finding outliers in a high-dimensional data set. We apply outlier detection techniques used in data mining to devise a linear time algorithm to extract the salient features. This yields a definition of saliency which rests on a more principled basis and also produces more reliable feature correspondences between images than the more conventional ones.
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
Breunig M. M., Kriegel, H.-P., Ng, R., Sander, J. “LOF: Identifying Density-Based Local Outliers,” Proc. ACM SIGMOD Int. Conf. on Management of Data, (2000).
Delaert, F., Seitz, S. M, Thorpe, C. E., Thrun, S., “Structure from Motion Without Correspondences,” Proc. Computer Vision and Pattern Recognition Conf., (2000).
Freeman, W. T., and Adelson, E. H. “The design and use of steerable filters,” IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 9 (1991).
Hawkins, D., Identification of Outliers, Chapman and Hall, London, (1980).
Knorr, E., Ng, R. “Algorithms for Mining Distance-based Outliers in Large Datasets,” Proc. of 24th Int. Conf. On Very Large Data Bases, (1998).
Leclerc, Y.G., Q.T. Luong, et al., “Self-consistency: A novel approach to characterizing the accuracy and reliability of point correspondence algorithms,” DARPA Image Understanding Workshop, (1998)
Lisin, D., Riseman, E., Hanson, A. “Extracting Salient Image Fetures Using Outlier Detection Techniques,” TR UM-CS-2003-002, Dept. of Comp. Sci., UMASS Amherst, (2003)
Lindeberg, T. “Feature detection with automatic scale selection,” Intl. Journal of Computer Vision 30, 2 (1998).
Piater, J. Visual Feature Learning. Ph.D. dissertation, Dept. of Comp. Sci., UMASS Amherst, (2001).
Ravela, S. and A. Hanson, “On Multi-Scale Differential Features for Face Recognition,” Vision Interface, Ottawa, (2001).
Schultz, H., A. R. Hanson, E. M. Riseman, F. R. Stolle, D. Woo, Z. Zhu, “A Self-consistency Technique for Fusing 3D Information,” Invited talk presented at the IEEE 5th Intl. Conf. on Information Fusion, Annapolis, Maryland, (2002).
Shokoufandeh, A., Marsic, I., Dickinson, S.J. “View-Based Object Recognition Using Saliency Maps,” TR DCS-TR-339, Dept. of Comp. Sci., Rutgers U., (1998).
Walker, K. N., Cootes, T. F., Taylor, C. J. “Locating Salient Object Features,” Proc. of BMVC, (1998).
Zhang, Z., Deriche, R., Faugeras, O., and Luong, Q-T. “A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry,” Artificial Intelligence 78, 1–2, (1995).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lisin, D., Riseman, E., Hanson, A. (2003). Extracting Salient Image Features for Reliable Matching Using Outlier Detection Techniques. In: Crowley, J.L., Piater, J.H., Vincze, M., Paletta, L. (eds) Computer Vision Systems. ICVS 2003. Lecture Notes in Computer Science, vol 2626. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36592-3_46
Download citation
DOI: https://doi.org/10.1007/3-540-36592-3_46
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00921-4
Online ISBN: 978-3-540-36592-1
eBook Packages: Springer Book Archive