Skip to main content

SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

Abstract

Our goal is to detect boundaries of objects or surfaces occurring in an arbitrary image. We present a new approach that discovers boundaries by sequential labeling of a given set of image edges. A visited edge is labeled as on or off a boundary, based on the edge’s photometric and geometric properties, and evidence of its perceptual grouping with already identified boundaries. We use both local Gestalt cues (e.g., proximity and good continuation), and the global Helmholtz principle of non-accidental grouping. A new formulation of the Helmholtz principle is specified as the entropy of a layout of image edges. For boundary discovery, we formulate a new, policy iteration algorithm, called SLEDGE. Training of SLEDGE is iterative. In each training image, SLEDGE labels a sequence of edges, which induces loss with respect to the ground truth. These sequences are then used as training examples for learning SLEDGE in the next iteration, such that the total loss is minimized. For extracting image edges that are input to SLEDGE, we use our new, low-level detector. It finds salient pixel sequences that separate distinct textures within the image. On the benchmark Berkeley Segmentation Datasets 300 and 500, our approach proves robust and effective. We outperform the state of the art both in recall and precision for different input sets of image edges.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

References

  • Ahuja, N., & Todorovic, S. (2007). Learning the taxonomy and models of categories present in arbitrary images. In ICCV, Rio de Janeiro.

  • Ahuja, N., & Todorovic, S. (2008). Connected segmentation tree—A joint representation of region layout and hierarchy. In CVPR.

  • Arbelaez, P. (2006). Boundary extraction in natural images using ultrametric contour maps. In POCV (p. 182).

  • Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2010). Contour detection and hierarchical image segmentation. In TPAMI, 99(RapidPosts).

  • Belongie, S., Malik, J., & Puzicha, J. (2002). Shape matching and object recognition using shape contexts. TPAMI, 24(4), 509–522.

    Article  Google Scholar 

  • Biederman, I. (1988). Surface versus edge-based determinants of visual recognition. Cognitive Psychology, 20(1), 38–64.

    Article  Google Scholar 

  • Borenstein, E., & Ullman, S. (2002). Class-specific, top-down segmentation. In ECCV, Copenhagen (vol. 2, pp. 109–124).

  • Borgefors, G. (1988). Hierarchical Chamfer matching: A parametric edge matching algorithm. TPAMI, 10(6), 849–865.

    Article  Google Scholar 

  • Brice, C. R., & Fennema, C. L. (1970). Scene analysis using regions. Artificial Intelligence, 1, 205–226.

    Article  Google Scholar 

  • Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual web search engine. In Seventh international world-wide web conference (WWW : 1998).

  • Canny, J. (1986). A computational approach to edge detection. TPAMI, 8(6), 679–698.

    Article  Google Scholar 

  • Coughlan, J. M., & Yuille, A. L. (2002). Bayesian A* tree search with expected o(n) node expansions: Applications to road tracking. Neural Computation, 14(8), 1929–1958.

    MATH  Article  Google Scholar 

  • Daume, H., III, Langford, J., & Marcu, D. (2009). Search-based structured prediction. Machine Learning Journal.

  • Deng, Y., & Manjunath, B. S. (2001). Unsupervised segmentation of color-texture regions in images and videos. TPAMI, 23(8), 800–810.

    Article  Google Scholar 

  • Desolneux, A., Moisan, L., & Morel, J. (2001). Edge detection by Helmholtz principle. Journal of Mathematical Imaging and Vision, 14(3), 271–284.

    MATH  Article  Google Scholar 

  • Desolneux, A., Moisan, L., & Morel, J.-M. (2000). Meaningful alignments. IJCV, 40(1), 7–23.

    MATH  Article  Google Scholar 

  • Desolneux, A., Moisan, L., & Morel, J. -M. (2003). A grouping principle and four applications. TPAMI, 25(4), 508–513.

    Google Scholar 

  • Dietterich, T. G. (2000). Ensemble methods in machine learning. In Lecture Notes in Computer Science (pp. 1–15).

  • Dollar, P., Tu Z., Belongie, S. (2006). Supervised learning of edges and object boundaries. In CVPR (pp. 1964–1971).

  • Donoser, M., Riemenschneider, H., & Bischof, H. (2010). Linked edges as stable region boundaries. In CVPR.

  • Drummond, C., & Holte, R. C. (2003). C4.5, class imbalance, and cost sensitivity: Why under-sampling beats over-sampling. In Workshop on learning from imbalanced datasets II.

  • Felzenszwalb, P., & McAllester, D. (2006). A min-cover approach for finding salient curves. In POCV.

  • Ferrari, V., Jurie, F., & Schmid, C. (2010). From images to shape models for object detection. IJCV, 87(3), 284–303.

    Article  Google Scholar 

  • Freund, Y., Mansour, Y., & Schapire, R. E. (2001) Why averaging classifiers can protect against overfitting. In Proceedings of the 8th international workshop on artificial intelligence and statistics.

  • Fridman, A. (2003). Mixed markov models. Proceedings of the National Academy of Sciences, 100(14), 8092–8096.

    MathSciNet  MATH  Article  Google Scholar 

  • Galun, M., Basri, R., & Brandt, A. (2007). Multiscale edge detection and fiber enhancement using differences of oriented means. In ICCV (pp. 1–8).

  • Geman, D., & Jedynak, B. (1996). An active testing model for tracking roads in satellite images. TPAMI, 18(1), 1–14.

    Article  Google Scholar 

  • Greminger, M. A., & Nelson, B. J. (2008). A deformable object tracking algorithm based on the boundary element method that is robust to occlusions and spurious edges. IJCV, 78(1), 29–45.

    Article  Google Scholar 

  • Guy, G., & Medioni, G. (1996). Inferring global perceptual contours from local features. IJCV, 20(1–2), 113–133.

    Article  Google Scholar 

  • Helmholtz, H. (1962). Treatise on physiological optics (first published in 1867). New York: Dover.

    Google Scholar 

  • Hochberg, J. E. (1957). Effects of the Gestalt revolution: The Cornell symposium on perception. Psychological Review, 64(2), 73–84.

    Article  Google Scholar 

  • Itti, L., & Koch, C. (2001). Computational modeling of visual attention. Nature Reviews Neuroscience, 2(3), 194–203.

    Article  Google Scholar 

  • Jain, A., Gupta, A., & Davis, L. S. (2010). Learning what and how of contextual models for scene labeling. ECCV, 4, 199–212.

  • Jermyn, I. H., & Ishikawa, H. (2001). Globally optimal regions and boundaries as minimum ratio weight cycles. TPAMI, 23(10), 1075–1088.

    Article  Google Scholar 

  • Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement learning: A survey. JAIR, 4, 237–285.

    Google Scholar 

  • Kim, G., Faloutsos, C., & Hebert, M. (2008). Unsupervised modeling of object categories using link analysis techniques. In CVPR.

  • Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998). On combining classifiers. TPAMI, 20, 226–239.

    Article  Google Scholar 

  • Koffka, K. (1935). Principles of Gestalt psychology. London: Routledge.

    Google Scholar 

  • Kokkinos, I. (2010). Boundary detection using F-measure-, Filter- and Feature- (\({F}^3\)) boost. In ECCV.

  • Kokkinos, I. (2010). Highly accurate boundary detection and grouping. In CVPR.

  • Konishi, S., Yuille, A., Coughlan, J., & Zhu, S.-C. (1999). Fundamental bounds on edge detection: An information theoretic evaluation of different edge cues. In CVPR.

  • Konishi, S., Yuille, A. L., Coughlan, J. M., & Zhu, S. C. (2003). Statistical edge detection: Learning and evaluating edge cues. TPAMI, 25, 57–74.

    Article  Google Scholar 

  • Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, Williamstown (pp. 282–289).

  • Lee, Y., & Grauman, K. (2009). Shape discovery from unlabeled image collections. In CVPR.

  • Lindeberg, T. (1998). Edge detection and ridge detection with automatic scale selection. IJCV, 30(2), 117–156.

    Article  Google Scholar 

  • Lowe, D. G. (1985). Perceptual organization and visual recognition. Norwell: Kluwer Academic Publishers.

    Book  Google Scholar 

  • Mahamud, S., Williams, L. R., Thornber, K. K., & Xu, K. (2003). Segmentation of multiple salient closed contours from real images. TPAMI, 25(4), 433–444.

    Article  Google Scholar 

  • Mairal, J., Leordeanu, M., Bach, F., Hebert, M., & Ponce, J. (2008). Discriminative sparse image models for class-specific edge detection and image interpretation. In ECCV (pp. 43–56).

  • Maire, M., Arbelaez, P., Fowlkes, C., & Malik, J. (2008). Using contours to detect and localize junctions in natural images. In CVPR (pp. 1–8).

  • Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In ICCV, Vancouver.

  • Martin, D. R., Fowlkes, C. C., & Malik, J. (2004). Learning to detect natural image boundaries using local brightness, color, and texture cues. PAMI, 26, 530–549.

    Article  Google Scholar 

  • Morrone, M. C., & Owens, R. A. (1987). Feature detection from local energy. Pattern Recognition Letters, 6(5), 303–313.

    Article  Google Scholar 

  • Palmer, S. (1999). Vision science: Photons to phenomenology. Cambridge: MIT Press.

  • Perona, P., & Malik, J. (1990). Detecting and localizing edges composed of steps, peaks and roofs. In ICCV.

  • Porrill, J., & Pollard, S. (1991). Curve matching and stereo calibration. IVC, 9(1), 45–50.

    Article  Google Scholar 

  • Ren, X. (2008). Multi-scale improves boundary detection in natural images. In ECCV, Marseille.

  • Ren, X., Fowlkes, C., & Malik, J. (2008). Learning probabilistic models for contour completion in natural images. IJCV, 77(1–3), 47–63.

    Article  Google Scholar 

  • Rubner Y., & Tomasi C., (1996). Coalescing texture descriptors. In ARPA image understanding, Workshop (pp. 927–935).

  • Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008). Labelme: A database and web-based tool for image annotation. IJCV, 77(1–3), 157–173.

    Article  Google Scholar 

  • Sharon, E., Br ,A., & Basri, R. (2001). Segmentation and boundary detection using multiscale intensity measurements. In CVPR (pp. 469–476).

  • Shashua, A., & Ullman, S. (1988). Structural saliency: The detection of globally salient structures using a locally connected network. In ICCV, Tampa.

  • Taskar, B., Guestrin, C., & Koller, D. (2004). Max-margin Markov networks. In NIPS, Vancouver.

  • Teh, C. H., & Chin, R. T. (1989). On the detection of dominant points on digital curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(8), 859–872.

    Article  Google Scholar 

  • Tsochantaridis, I., Joachims, T., Hofmann, T., & Altun, Y. (2005). Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6, 1453–1484.

    MathSciNet  MATH  Google Scholar 

  • Varma, M., & Zisserman, A. (2003). Texture classification: Are filter banks necessary? CVPR, 2, 691.

    Google Scholar 

  • Wang, S., Kubota, T., Siskind, J. M., & Wang, J. (2005). Salient closed boundary extraction with ratio contour. TPAMI, 27(4), 546–561.

    Article  Google Scholar 

  • Will, S., Hermes, L., Buhmann, J. M., Puzicha, & J. (2000). On learning texture edge detectors. In ICIP (pp. 877–880).

  • Williams, L., & Jacobs, D. (1995). Stochastic completion fields: A neural model of illusory contour shape and salience. In ICCV (pp. 408–415).

  • Williams, L. R., & Thornber, K. K. (1999). A comparison of measures for detecting natural shapes in cluttered backgrounds. IJCV, 34(2–3), 81–96.

    Article  Google Scholar 

  • Xiong, W., & Jia, J. (2007). Stereo matching on objects with fractional boundary. In CVPR.

  • Yu, S. (2005). Segmentation induced by scale invariance. In CVPR.

  • Zhu, Q., Song, G., & Shi, J. (2007). Untangling cycles for contour grouping. In ICCV (pp. 1–8).

  • Zhu, S.-C. (1999). Embedding Gestalt laws in Markov random fields. TPAMI, 21(11), 1170–1187.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sinisa Todorovic.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Payet, N., Todorovic, S. SLEDGE: Sequential Labeling of Image Edges for Boundary Detection. Int J Comput Vis 104, 15–37 (2013). https://doi.org/10.1007/s11263-013-0612-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-013-0612-5

Keywords

  • Training Image
  • Voronoi Diagram
  • Ranking Function
  • Object Boundary
  • Image Edge