Abstract
The joint tasks of object recognition and object segmentation from a single image are complex in their requirement of not only correct classification, but also deciding exactly which pixels belong to the object. Exploring all possible pixel subsets is prohibitively expensive, leading to recent approaches which use unsupervised image segmentation to reduce the size of the configuration space. Image segmentation, however, is known to be unstable, strongly affected by small image perturbations, feature choices, or different segmentation algorithms. This instability has led to advocacy for using multiple segmentations of an image. In this paper, we explore the question of how to best integrate the information from multiple bottom-up segmentations of an image to improve object recognition robustness. By integrating the image partition hypotheses in an intuitive combined top-down and bottom-up recognition approach, we improve object and feature support. We further explore possible extensions of our method and whether they provide improved performance. Results are presented on the MSRC 21-class data set and the Pascal VOC2007 object segmentation challenge.
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
Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. PAMI 29 (2007)
Malisiewicz, T., Efros, A.A.: Improving spatial support for objects via multiple segmentations. In: BMVC (2007)
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 (2001)
Russell, B., Efros, A., Sivic, J., Freeman, W., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)
Pantofaru, C., Dorkó, G., Schmid, C., Hebert, M.: Combining regions and patches for object class localization. In: Beyond Patches Workshop, CVPR (2006)
Hoiem, D., Efros, A., Hebert, M.: Recovering surface layout from an image. IJCV 75 (2007)
Azran, A., Ghahramani, Z.: Spectral methods for automatic multiscale data clustering. In: CVPR (2006)
Tu, Z., Chen, Z., Yuille, A.L., Zhu, S.C.: Image parsing: Unifying segmentation, detection, and recognition. IJCV (2005)
Borenstein, E., Malik, J.: Shape guided object segmentation. In: CVPR (2006)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI (2002)
Fowlkes, C., Martin, D., Malik, J.: Learning affinity functions for image segmentation: Combining patch-based and gradient-based approaches. In: CVPR (2003)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. PAMI (2003)
Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)
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)
Winn, J., Jojic, N.: Locus: Learning object classes with unsupervised segmentation. In: ICCV (2005)
Tu, Z., Zhu, S.C.: Image segmentation by data-driven markov chain monte carlo. PAMI 24, 657–673 (2002)
Verbeek, J., Triggs, B.: Region classification with markov field aspect models. In: CVPR (2007)
Winn, J., Shotton, J.: The layout consistent random field for recognizing and segmenting partially occluded objects. In: CVPR (2006)
Kumar, M., Torr, P., Zisserman, A.: Obj cut. In: CVPR (2005)
Leibe, B., Schiele, B.: Interleaved object categorization and segmentation. In: BMVC (2003)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: The MSRC 21-class object recognition database (2006)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL VOC 2007 (2007), http://www.pascal-network.org/challenges/VOC/voc2007
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines, Software (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
Wu, T.F., Lin, C.J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. Journal of Machine Learning Research 5, 975–1005 (2004)
van de Weijer, J., Schmid, C.: Coloring local feature extraction. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951. Springer, Heidelberg (2006)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Ladicky, L., Kohli, P., Torr, P.: Oxford Brookes entry, PASCAL VOC 2007 Segmentation Challenge (2007), http://www.pascal-network.org/challenges/VOC/voc2007
Viitaniemi, V.: Helsinki University of Technology, PASCAL VOC 2007 Challenge (2007), http://www.pascal-network.org/challenges/VOC/voc2007
Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV (2003)
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Annals of Statistics (2000)
Collins, M., Schapire, R., Singer, Y.: Logistic regression, Adaboost and Bregman distances. Machine Learning (2002)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. PAMI 23, 1222–1239 (2001)
Russell, B., Torralba, A., Murphy, K., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. IJCV (2007)
von Ahn, L., Liu, R., Blum, M.: Peekaboom: A game for locating objects in images. In: ACM CHI (2006)
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
Pantofaru, C., Schmid, C., Hebert, M. (2008). Object Recognition by Integrating Multiple Image Segmentations. 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_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-88690-7_36
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)