Abstract
Contour fragments are adept to interpret the characteristics of object boundaries, but difficult to encode the information of object interior region. In this paper, inspired by the Gestalt principles that people can perceive object interior region by grouping similar and proximate fragments, we propose to pair contour fragments to encode more information of object interior region. To this end, we propose a pairing algorithm to generate Contour Fragment Pairs (CFPs). According to the proposed algorithm, the fragments of a valid CFP are required to be: co-occurrent over the training images, similar in shape, and proximate with each other. With a valid CFP, we can represent object shape using its fragments and object interior region using the region between its fragments. Finally, we design a boosting algorithm to select and assemble many CFPs into a classifier. The proposed classifier is competent for localizing objects with bounding boxes, delineating boundary and segmenting foreground. Moreover, the method possesses another merit that it only requires annotated bounding boxes as training data. Experiments on the public datasets show that the proposed approach achieves very promising performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, X., Wang, X., Latecki, L.J., Liu, W., Tu, Z.: Active skeleton for non-rigid object detection. In: ICCV (2009)
Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. In: PAMI (2008)
Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. In: IJCV (2010)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Object detection by contour segment networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 14–28. Springer, Heidelberg (2006)
Hu, W., Wu, Y.N., Zhu, S.C.: Image representation by active curves. In: ICCV (2011)
Koffka, K.: Principles of Gestalt Psychology (1935)
Levinshtein, A., Sminchisescu, C., Dickinson, S.: Optimal contour closure by superpixel grouping. In: ECCV (2012)
Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. In: ACM Transactions on Graphics (2004)
Shotton, J., Blake, A., Cipolla, R.: Multi-scale categorical object recognition using contour fragments. In: PAMI (2008)
Srinivasan, P., Zhu, Q., Shi, J.: Many-to-one contour matching for describing and discriminating object shape. In: CVPR (2010)
Toshev, A., Taskar, B., Daniilidis, K.: Shape-based object detection via boundary structure segmentation. In: IJCV (2012)
Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. In: PAMI (2008)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. In: PAMI (2002)
Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detector. In: IJCV (2007)
Zheng, W., Liang, L.: Fast car detection using image strip features. In: CVPR (2009)
Zheng, W., Song, S., Chang, H., Chen, X.: Grouping active contour fragments for object recognition. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 289–301. Springer, Heidelberg (2013)
Yang, X., Latecki, L.J.: Weakly supervised shape based object detection with particle filter. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 757–770. Springer, Heidelberg (2010)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2015)
Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast human detection using a cascade of histograms of oriented gradients. In: CVPR (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Zheng, W., Zhang, Q., Li, Z., Xiong, J. (2016). Pairing Contour Fragments for Object Recognition. In: Tian, Q., Sebe, N., Qi, GJ., Huet, B., Hong, R., Liu, X. (eds) MultiMedia Modeling. MMM 2016. Lecture Notes in Computer Science(), vol 9516. Springer, Cham. https://doi.org/10.1007/978-3-319-27671-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-27671-7_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27670-0
Online ISBN: 978-3-319-27671-7
eBook Packages: Computer ScienceComputer Science (R0)