Abstract
Region (pixel) labeling has attracted increasing attentions from both research and industry communities. In this paper, we present a new approach based on Conditional Random Fields (CRF) to assign the semantic labels to the corresponding regions of images. Different from previous work, our model incorporates the global observation into the region labeling framework with the harness of spatial context modeling of CRF model. The experimental results with two commonly used datasets demonstrate that our method achieves significant improvement on region labeling tasks compared with the strong baselines.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Liu, X., Cheng, B., Yan, S.: Label to region by bi-layer sparsity priors. In: MM (2009)
Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional Random Fields: Probabilisitc Models for Segmenting and Labeling Sequence Data. In: ICML (2001)
Huang, Q., Han, M., Wu, B., Ioffe, S.: A hierarchical Conditional Random Field model for labeling and segmenting images of Street Scenes. In: CVPR (2011)
Kohli, P., Ladicky, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. In: CVPR (2008)
Athanasiadis, T., Mylonas, P., Avrithis, Y.: A context-based region labeling approach for semantic image segmentation. In: Avrithis, Y., Kompatsiaris, Y., Staab, S., O’Connor, N.E. (eds.) SAMT 2006. LNCS, vol. 4306, pp. 212–225. Springer, Heidelberg (2006)
Vezhnevets, A., Ferrari, V., Buhmann, J.M.: Weakly supervised semantic Segmentation with a multi-image model. In: ICCV (2011)
Tang, J., Zha, Z.-J., Tao, D., Chua, T.-S.: Semantic-Gap Oriented Active Learning for Multi-Label Image Annotation. IEEE Tran. on Image Processing 21(4) (2012)
Tang, J., Hong, R., Yan, S., Chua, T.-S., Qi, G.-J., Jain, R.: Image Annotation by kNN-Sparse Graph-based Label Propagation over Noisily-Tagged Web Images. ACM Tran. on Intelligent Systems and Technology 2(2) (2011)
Liu, J., Xu, C., Lu, H.: Cross-media retrieval: state-of-the-art and open issues. International Journal of Multimedia Intelligence and Security 1(1) (2010)
Liu, C., Yuen, J., Torralba, A.: Nonparametric Scene Parsing via Label Transfer. IEEE Tranactions on Pattern Analysis and Machine Intelligence 33(12) (2011)
Rubinstein, M., Liu, C., Freeman, W.T.: Annotation Propagation in Large Image Databased via Dense Image Correspondence. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 85–99. Springer, Heidelberg (2012)
Kumar, S., Hebert, M.: Discriminative Fields for Modeling Spatial Dependencies in Natural Images. In: NIPS (2003)
Corso, J.J., Yuille, A., Tu, Z.: Graph-shifts: Natural Image Labeling by Dynamic Hierarchical Computing. In: CVPR (2008)
Galleguillos, G., Rabinovich, A., Belogie, S.: Objet categorization using co-occurrence, location and appearance. In: CVPR (2008)
Russel, B.C., Torralba, A., Murphy, K.P., Freenam, W.T.: Labelme: a database and web-based tool for image annotation. International Journal of Computer Vision 77(1-3), 157–173 (2008)
Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
He, X., Zemel, R.S., Carreira-Perpinan, M.A.: Multiscale Conditional Random Fields for Image Labeling. In: CVPR (2004)
Toyoda, T., Hasegawa, O.: Random Field Model for Integration of Local Information and Global Information. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(8), 1483–1489 (2008)
Fan, R., Chang, K., Hsieh, C., Wang, X., Lin, C.: LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research 9, 1871–1874 (2008)
Xiang, Y., Zhou, X., Chua, T.-S., Ngo, C.-W.: A revisit of generative model for automatic image annotation using markov random fields. In: CVPR 2009 (2009)
http://research.microsoft.com/en-us/projects/objectclassrecognition
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Lin, Z., Chan, W., He, K., Zhou, X., Wang, M. (2013). Conditional Random Fields for Image Region Labeling with Global Observation. In: Huet, B., Ngo, CW., Tang, J., Zhou, ZH., Hauptmann, A.G., Yan, S. (eds) Advances in Multimedia Information Processing – PCM 2013. PCM 2013. Lecture Notes in Computer Science, vol 8294. Springer, Cham. https://doi.org/10.1007/978-3-319-03731-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-03731-8_54
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03730-1
Online ISBN: 978-3-319-03731-8
eBook Packages: Computer ScienceComputer Science (R0)