Abstract
In this work we empirically study the multi-scale boundary detection problem in natural images. We utilize local boundary cues including contrast, localization and relative contrast, and train a classifier to integrate them across scales. Our approach successfully combines strengths from both large-scale detection (robust but poor localization) and small-scale detection (detail-preserving but sensitive to clutter). We carry out quantitative evaluations on a variety of boundary and object datasets with human-marked groundtruth. We show that multi-scale boundary detection offers large improvements, ranging from 20% to 50%, over single-scale approaches. This is the first time that multi-scale is demonstrated to improve boundary detection on large datasets of natural images.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Canny, J.: A computational approach to edge detection. IEEE Trans. PAMI 8, 679–698 (1986)
Witkin, A.: Scale-space filtering. Int’l. J. Conf. on Artificial Intell. 2, 1019–1022 (1983)
Koenderink, J.: The structure of images. Biological Cybernetics 50, 363–370 (1984)
Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, Dordrecht (1994)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. PAMI 12, 629–639 (1990)
Lindeberg, T.: Edge detection and ridge detection with automatic scale selection. Int’l. J. Comp. Vision 30, 117–156 (1998)
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: ICCV, vol. II, pp. 416–423 (2001)
Konishi, S., Yuille, A., Coughlan, J., Zhu, S.: Fundamental bounds on edge detection: an information theoretic evaluation of different edge cues. In: CVPR, pp. 573–579 (1999)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Trans. PAMI 26(5), 530–549 (2004)
Konishi, S., Yuille, A., Coughlan, J.: A statistical approach to multi-scale edge detection. In: ECCV Workshop on Generative-Model-Based Vision (2002)
Dollar, P., Tu, Z., Belongie, S.: Supervised learning of edges and object boundaries. In: CVPR, vol. 2, pp. 1964–1971 (2006)
Galun, M., Basri, R., Brandt, A.: Multiscale edge detection and fiber enhacement using differences of oriented means. In: ICCV (2007)
Bouman, C., Shapiro, M.: A multiscale random field model for bayesian image segmentation. IEEE Trans. Im. Proc. 3(2), 162–177 (1994)
Koepfler, G., Lopez, C., Morel, J.: A multiscale algorithm for image segmentation by variational method. SIAM J. Numer. Anal. 31(1), 282–299 (1994)
Sharon, E., Brandt, A., Basri, R.: Segmentation and boundary detection using multiscale intensity measurements. In: CVPR (2001)
Ruderman, D.L., Bialek, W.: Statistics of natural images: Scaling in the woods. Physics Review Letters 73(6), 814–817 (1994)
Elder, J., Goldberg, R.: Ecological statistics of gestalt laws for the perceptual organization of contours. Journal of Vision 2(4), 324–353 (2002)
Ren, X., Malik, J.: A probabilistic multi-scale model for contour completion based on image statistics. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 312–327. Springer, Heidelberg (2002)
Bergholm, F.: Edge focusing. IEEE Trans. PAMI 9, 726–741 (1987)
Basu, M.: Gradient-based edge detection methods - a survey. IEEE. Trans. System, Man and Cybernatics 32(3), 252–260 (2002)
Rijsbergen, C.V.: Information Retrieval, 2nd edn. Univ. of Glasgow (1979)
Ren, X., Fowlkes, C., Malik, J.: Scale-invariant contour completion using conditional random fields. In: ICCV, vol. 2, pp. 1214–1221 (2005)
Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: Workshop on Perceptual Organization in Computer Vision (POCV) (2006)
Felzenszwalb, P., McAllester, D.: A min-cover approach for finding salient curves. In: Workshop on Perceptual Organization in Computer Vision (POCV) (2006)
Zhu, Q., Song, G., Shi, J.: Untangling cycles for contour grouping. In: ICCV (2007)
Stein, A., Hoiem, D., Hebert, M.: Learning to find object boundaries using motion cues. In: ICCV (2007)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951. Springer, Heidelberg (2006)
Malisiewicz, T., Efros, A.: Improving spatial support for objects via multiple segmentations. In: BMVC (2007)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge (VOC 2007). (2007), http://www.pascal-network.org/challenges/VOC/voc2007/workshop/
Russell, B., Torralba, A., Murphy, K., Freeman, W.: LabelMe: a database and web-based tool for image annotation. Technical Report AI Memo AIM-2005-025, MIT (2005)
Martin, D., Fowlkes, C., Walker, L., Malik, J.: Local boundary detection in natural images: Matching human and machine performance. In: ECVP (2003)
Yu, S.: Segmentation induced by scale invariance. In: CVPR, vol. I, pp. 445–451 (2005)
Estrada, F., Elder, J.: Multi-scale contour extraction based on natural image statistics. In: Workshop on Perceptual Organization in Computer Vision (POCV) (2006)
Hoiem, D., Efros, A., Hebert, M.: Recovering occlusion boundaries from a single image. In: ICCV (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ren, X. (2008). Multi-scale Improves Boundary Detection in Natural Images. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5304. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88690-7_40
Download citation
DOI: https://doi.org/10.1007/978-3-540-88690-7_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88689-1
Online ISBN: 978-3-540-88690-7
eBook Packages: Computer ScienceComputer Science (R0)