Advertisement

International Journal of Computer Vision

, Volume 94, Issue 2, pp 154–174 | Cite as

Coding Images with Local Features

  • Timo Dickscheid
  • Falko Schindler
  • Wolfgang Förstner
Article

Abstract

We develop a qualitative measure for the completeness and complementarity of sets of local features in terms of covering relevant image information. The idea is to interpret feature detection and description as image coding, and relate it to classical coding schemes like JPEG. Given an image, we derive a feature density from a set of local features, and measure its distance to an entropy density computed from the power spectrum of local image patches over scale. Our measure is meant to be complementary to existing ones: After task usefulness of a set of detectors has been determined regarding robustness and sparseness of the features, the scheme can be used for comparing their completeness and assessing effects of combining multiple detectors. The approach has several advantages over a simple comparison of image coverage: It favors response on structured image parts, penalizes features in purely homogeneous areas, and accounts for features appearing at the same location on different scales. Combinations of complementary features tend to converge towards the entropy, while an increased amount of random features does not. We analyse the complementarity of popular feature detectors over different image categories and investigate the completeness of combinations. The derived entropy distribution leads to a new scale and rotation invariant window detector, which uses a fractal image model to take pixel correlations into account. The results of our empirical investigations reflect the theoretical concepts of the detectors.

Keywords

Local features Complementarity Information theory Coding Keypoint detectors Local entropy 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bay, H., Ferrari, V., & Gool, L. V. (2005). Wide-baseline stereo matching with line segments. In Proceedings of the IEEE conference on computer vision and pattern recognition, Washington, DC, USA (Vol. 1, pp. 329–336). Google Scholar
  2. Bercher, J. F., & Vignat, C. (2000). Estimating the entropy of a signal with applications. IEEE Transactions on Signal Processing, 48(6), 1687–1694. CrossRefGoogle Scholar
  3. Berger, T. (1971). Rate distortion theory: a mathematical basis for data compression. Englewood Cliffs: Prentice-Hall. Google Scholar
  4. Bigün, J. (1990). A structure feature for some image processing applications based on spiral functions. Computer Vision, Graphics and Image Processing, 51(2), 166–194. CrossRefGoogle Scholar
  5. Bishop, C. M. (2006). Information Science and Statistics. Pattern recognition and machine learning. Berlin: Springer. zbMATHGoogle Scholar
  6. Cayton, L., & Dasgupta, S. (2006). Robust Euclidean embedding. In Proceedings of the international conference on machine learning (pp. 169–176). New York: ACM. Google Scholar
  7. Corso, J. J., & Hager, G. D. (2009). Image description with features that summarize. Computer Vision and Image Understanding, 113(4), 446–458. CrossRefGoogle Scholar
  8. Davis, G. M., & Nosratinia, A. (1998). Wavelet-based image coding: an overview. Applied and Computational Control, Signals, and Circuits, 1, 205–269. Google Scholar
  9. Davisson, L. D. (1972). Rate-distortion theory and application. Proceedings of the IEEE, 60, 800–808. CrossRefGoogle Scholar
  10. Dickscheid, T., & Förstner, W. (2009). Evaluating the suitability of feature detectors for automatic image orientation systems. In Proceedings of the international conference on computer vision systems, Liege, Belgium (pp. 305–314). Google Scholar
  11. Förstner, W. (1994). A framework for low level feature extraction. In Proceedings of the European conference on computer vision, Stockholm, Sweden (Vol. III, pp. 383–394). Google Scholar
  12. Förstner, W. (1998). Image preprocessing for feature extraction in digital intensity, color and range images. In Lecture notes in earth sciences : Vol. 95/2000. Geomatic methods for the analysis of data in earth sciences (pp. 165–189). Berlin: Springer. Google Scholar
  13. Förstner, W., & Gülch, E. (1987). A fast operator for detection and precise location of distinct points, corners and centres of circular features. In ISPRS conference on fast processing of photogrammetric data, Interlaken (pp. 281–305). Google Scholar
  14. Förstner, W., Dickscheid, T., & Schindler, F. (2009). Detecting interpretable and accurate scale-invariant keypoints. In Proceedings of the IEEE international conference on computer vision, Kyoto, Japan. Google Scholar
  15. Haja, A., Jähne, B., & Abraham, S. (2008). Localization accuracy of region detectors. In Proceedings of the IEEE conference on computer vision and pattern recognition. Google Scholar
  16. Harris, C., & Stephens, M. J. (1988). A combined corner and edge detector. In Proceedings of the Alvey vision conference (pp. 147–152). Google Scholar
  17. Heath, M., Sarkar, S., Sanocki, T., & Bowyer, K. (1996). Comparison of edge detectors: a methodology and initial study. In Proceedings of the IEEE conference on computer vision and pattern recognition (p. 143). Google Scholar
  18. Kadir, T., & Brady, M. (2001). Saliency, scale and image description. International Journal of Computer Vision, 45(2), 83–105. zbMATHCrossRefGoogle Scholar
  19. Kadir, T., Zisserman, A., & Brady, M. (2004). An affine invariant salient region detector. In Proceedings of the European conference on computer vision (pp. 228–241). Berlin: Springer. Google Scholar
  20. Kovesi, P. D. (2009). MATLAB and Octave functions for computer vision and image processing. School of Computer Science & Software Engineering, The University of Western Australia, http://www.csse.uwa.edu.au/~pk/research/matlabfns/.
  21. Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In Proceedings of the IEEE conference on computer vision and pattern recognition, Washington, DC, USA (pp. 2169–2178). Google Scholar
  22. Li, F. F., & Perona, P. (2005). A Bayesian hierarchical model for learning natural scene categories. In Proceedings of the IEEE conference on computer vision and pattern recognition (Vol. 2, pp. 524–531). Los Alamitos: IEEE Comput. Soc. Google Scholar
  23. Liang, P., Jordan, M. I., & Klein, D. (2010). Probabilistic grammars and hierarchical Dirichlet processes. In The Oxford handbook of applied Bayesian analysis. London: Oxford University Press. Google Scholar
  24. Lillholm, M., Nielsen, M., & Griffin, L. D. (2003). Feature-based image analysis. International Journal of Computer Vision, 52(2–3), 73–95. CrossRefGoogle Scholar
  25. Lindeberg, T. (1998a). Edge detection and ridge detection with automatic scale selection. International Journal of Computer Vision, 30(2), 117–156. CrossRefGoogle Scholar
  26. Lindeberg, T. (1998b). Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2), 79–116. CrossRefGoogle Scholar
  27. Liu, C., Szeliski, R., BingKang, S., Zitnick, C. L., & Freeman, W. T. (2008). Automatic estimation and removal of noise from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 299–314. CrossRefGoogle Scholar
  28. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110. CrossRefGoogle Scholar
  29. Marr, D. (1982). Vision: a computational investigation into the human representation and processing of visual information. New York: Freeman. Google Scholar
  30. Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004). Robust wide baseline stereo from maximally stable extremal regions. Image and Vision Computing, 22, 761–767. CrossRefGoogle Scholar
  31. McClure, D. E. (1980). Image models in pattern theory. Computer Graphics and Image Processing, 12(4), 309–325. MathSciNetCrossRefGoogle Scholar
  32. McGillem, C., & Svedlow, M. (1976). Image registration error variance as a measure of overlay quality. IEEE Transactions on Geoscience Electronics, 14(1), 44–49. CrossRefGoogle Scholar
  33. Meltzer, J., & Soatto, S. (2008). Edge descriptors for robust wide-baseline correspondence. In Proceedings of the IEEE conference on computer vision and pattern recognition. Google Scholar
  34. Mikolajczyk, K., & Schmid, C. (2004). Scale and affine invariant interest point detectors. International Journal of Computer Vision, 60(1), 63–86. CrossRefGoogle Scholar
  35. Mikolajczyk, K., Zisserman, A., & Schmid, C. (2003). Shape recognition with edge-based features. In Proceedings of the British machine vision conference, Norwich, UK (pp. 779–788). Google Scholar
  36. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., & Gool, L. V. (2005). A comparison of affine region detectors. International Journal of Computer Vision, 65(1/2), 43–72. CrossRefGoogle Scholar
  37. Moreels, P., & Perona, P. (2007). Evaluation of features detectors and descriptors based on 3D objects. International Journal of Computer Vision, 73(3), 263–284. CrossRefGoogle Scholar
  38. Mumford, D. (2005). Empirical statistics and stochastic models for visual signals. In S. Haykin, J. Principe, T. Sejnowski, & J. McWhirter (Eds.), New directions in statistical signal processing: from systems to brain. Cambridge: MIT Press. Google Scholar
  39. Olshausen, B. A., & Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381(6583), 607–609. CrossRefGoogle Scholar
  40. Perďoch, M., Matas, J., & Obdržálek, Š. (2007). Stable affine frames on isophotes. In D. Metaxas, B. Vemuri, A. Shashua, & H. Shum (Eds.), Proceedings of IEEE international conference on computer vision (p. 8). Los Alamitos: IEEE Comput. Soc. Google Scholar
  41. Puzicha, J., Hofmann, T., & Buhmann, J. M. (1999). Histogram clustering for unsupervised image segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition, Ft. Collins, USA (pp. 602–608). Google Scholar
  42. Rosenfeld, A., & Kak, A. C. (1982). Digital picture processing. San Diego: Academic Press. Google Scholar
  43. Shannon, C. E. (1948). A mathematical theory of communication (Tech. Rep.). Bell System Technical Journal. Google Scholar
  44. Shi, J., & Tomasi, C. (1994). Good features to track. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 593–600). Google Scholar
  45. Smith, J. O. (2007). Mathematics of the discrete Fourier transform (DFT), W3K Publishing, Chap. 16.3. Google Scholar
  46. Tuytelaars, T., & Mikolajczyk, K. (2008). Local invariant feature detectors: a survey. Hanover: Now Publishers. Google Scholar
  47. Tuytelaars, T., & Van Gool, L. (2004). Matching widely separated views based on affine invariant regions. International Journal of Computer Vision, 59(1), 61–85. CrossRefGoogle Scholar
  48. Zeisl, B., Georgel, P., Schweiger, F., Steinbach, E., & Navab, N. (2009). Estimation of location uncertainty for scale invariant feature points. In Proceedings of the British machine vision conference, London, UK. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Timo Dickscheid
    • 1
  • Falko Schindler
    • 1
  • Wolfgang Förstner
    • 1
  1. 1.Department of PhotogrammetryInstitute of Geodesy and Geoinformation, University of BonnBonnGermany

Personalised recommendations