Abstract
This paper presents an overview of our recent work on shape-based object discovery in images. The overview focuses on the following related problems: (i) discovery of all distinct 2D object categories frequently occurring in an unlabeled set of images; (ii) learning a model of the discovered categories; and (iii) recognition and localization of objects from the discovered categories in new images. The paper argues that using image contours as basic features, and thus directly grounding object discovery and recognition on shape, offers a number of advantages in solving (i)–(iii) over more commonly used point features. Since shape is directly encoded by layouts of image contours, similar contour layouts across the images are expected to belong rather to object occurrences, than the background. The contour layouts are captured by a graph over all pairs of matching contours from different images. The graph’s maximum a posteriori multicoloring assignment is taken to represent the shapes of discovered objects. Our empirical evaluation suggests that shape is more expressive and discriminative than photometric features for object discovery.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Payet N, Todorovic S (2009) Matching hierarchies of deformable shapes. In: Proc 7th IAPR-TC-15 workshop graph-based representations in pattern recognition (GbR), pp 1–10
Payet N, Todorovic S (2010) From a set of shapes to object discovery. In: ECCV
Payet N, Todorovic S (2011) From contours to 3D object detection and pose estimation. In: ICCV (oral presentation)
Fergus R, Perona P, Zisserman A (2003) Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol 2, pp 264–271
Torralba A, Murphy K, Freeman W (2004) Sharing features: efficient boosting procedures for multiclass object detection. In: CVPR, vol 2, pp 762–769
Leibe B, Leonardis A, Schiele B (2004) Combined object categorization and segmentation with an implicit shape model. In: Workshop on statistical learning in computer vision, ECCV, pp 17–32
Agarwal S, Awan A, Roth D (2004) Learning to detect objects in images via a sparse, part-based representation. IEEE Trans Pattern Anal Mach Intell 26(11):1475–1490
Sudderth E, Torralba A, Freeman WT, Willsky AS (2005) Learning hierarchical models of scenes, objects, and parts. In: ICCV, vol 2, pp 1331–1338
Winn J, Criminisi A, Minka T (2005) Object categorization by learned universal visual dictionary. In: ICCV, vol 2, pp 1800–1807
Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28(4):594–611
Opelt A, Pinz A, Zisserman A (2006) Incremental learning of object detectors using a visual shape alphabet. In: CVPR, vol 1, pp 3–10
Biederman I (1988) Surface versus edge-based determinants of visual recognition. Cogn Psychol 20(1):38–64
Williams LR, Jacobs DW (1995) Stochastic completion fields: a neural model of illusory contour shape and salience. In: ICCV, pp 408–415
Lindenbaum M (1995) Bounds on shape recognition performance. IEEE Trans Pattern Anal Mach Intell 17(7):666–680
Liu TL, Geiger D (1999) Approximate tree matching and shape similarity. In: Proc IEEE int conf computer vision, vol 1, pp 456–462
Shokoufandeh A, Macrini D, Dickinson S, Siddiqi K, Zucker SW (2005) Indexing hierarchical structures using graph spectra. IEEE Trans Pattern Anal Mach Intell 27(7):1125–1140
Keselman Y, Dickinson S (2005) Generic model abstraction from examples. IEEE Trans Pattern Anal Mach Intell 27(7):1141–1156
Siddiqi K, Kimia BB (1996) A shock grammar for recognition. In: CVPR, p 507
Sebastian TB, Klein PN, Kimia BB (2004) Recognition of shapes by editing their shock graphs. IEEE Trans Pattern Anal Mach Intell 26(5):550–571
Felzenszwalb PF (2005) Representation and detection of deformable shapes. IEEE Trans Pattern Anal Mach Intell 27(2):208–220
Zhu Q, Wang L, Wu Y, Shi J (2008) Contour context selection for object detection: a set-to-set contour matching approach. In: ECCV (2), pp 774–787
Kokkinos I, Yuille AL (2009) HOP: hierarchical object parsing. In: CVPR
Ling H, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29(2):286–299
Torsello A, Robles-Kelly A, Hancock ER (2007) Discovering shape classes using tree edit-distance and pairwise clustering. Int J Comput Vis 72(3):259–285
Trinh NH, Kimia BB (2011) Skeleton search: category-specific object recognition and segmentation using a skeletal shape model. Int J Comput Vis 94(2):215–240
Bai X, Wang X, Liu W, Latecki LJ, Tu Z (2009) Active skeleton for non-rigid object detection. In: ICCV
Shotton J, Blake A, Cipolla R (2008) Multiscale categorical object recognition using contour fragments. IEEE Trans Pattern Anal Mach Intell 30(7):1270–1281
Ferrari V, Tuytelaars T, Gool LV (2006) Object detection by contour segment networks. In: ECCV, pp 14–28
Perona P, Malik J (1991) Detecting and localizing edges composed of steps, peaks and roofs. In: ICCV, pp 52–57
Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33:898–916
Felzenszwalb P, McAllester D (2006) A min-cover approach for finding salient curves. In: IEEE workshop on perceptual organization (POCV)
Russell BC, Freeman WT, Efros A, Sivic J, Zisserman A (2006) Using multiple segmentations to discover objects and their extent in image collections. In: CVPR
Todorovic S, Ahuja N (2008) Unsupervised category modeling, recognition, and segmentation in images. IEEE Trans Pattern Anal Mach Intell 30(12):1–17
Kim G, Faloutsos C, Hebert M (2008) Unsupervised modeling of object categories using link analysis techniques. In: CVPR
Lee YJ, Grauman K (2009) Shape discovery from unlabeled image collections. In: CVPR
Felzenszwalb P, McAllester D (2006) A min-cover approach for finding salient curves. In: CVPR POCV
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Chib S, Greenberg E (1995) Understanding the metropolis-hastings algorithm. Am Stat 49(4):327–335
Lin L, Zeng K, Liu X, Zhu SC (2009) Layered graph matching by composite cluster sampling with collaborative and competitive interactions. In: CVPR, June 2009
Lee YJ, Grauman K (2008) Foreground focus: unsupervised learning from partially matching images. In: BMVC
Fei-Fei L, Fergus R, Perona P (2004) Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: CVPR
Russell BC, Torralba A, Murphy KP, Freeman WT (2005) Labelme: a database and web-based tool for image annotation. Technical Report AIM-2005-025, MIT
Borenstein E, Ullman S (2002) Class-specific, top-down segmentation. In: ECCV, vol 2, pp 109–124
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Todorovic, S., Payet, N. (2013). Shape-Based Object Discovery in Images. In: Dickinson, S., Pizlo, Z. (eds) Shape Perception in Human and Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-5195-1_27
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5195-1_27
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5194-4
Online ISBN: 978-1-4471-5195-1
eBook Packages: Computer ScienceComputer Science (R0)