Abstract
This article proposed a progressive image segmentation, which allow users to segment images according to their preferences without any boring pre-labeling or training stages. We use an online learning method to train/update the segmentation model progressively. User can scribble on the image to label initial samples or correct the false-labeled regions of the result. To efficiently integrate the interaction with the learning and updating process, a three-level representation of images is built. The proposed method has three advantages. Firstly, the segmentation model can be learned online along with user’s manipulation without any pre-labeling. Secondly, the diversity of segmentation accord with user’s preferences can be met flexibly, and the more use the more accurate the segmentation could be. Finally, the segmentation model can be updated online to meet the needs of users. The experimental results demonstrate these advantages.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shotton, J., Winn, J., Rother, C., et al.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modelling texture, layout, and context. Int. J. Comput. Vis. 81(1), 2–23 (2009)
Gould, S., Rodgers, J., Cohen, D., et al.: Multi-class segmentation with relative location prior. Int. J. Comput. Vis. 80(3), 300–316 (2008)
Socher, R., Fei-Fei, L.: Connecting modalities: semi-supervised segmentation and annotation of images using unaligned text corpora. In: IEEE CVPR, pp. 966–973 (2010)
Rother, C., Minka, T., et al.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: IEEE CVPR, pp. 993–1000 (2006)
Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: CVPR (2010)
Kim, G., Xing, E.P., Fei-Fei, L., et al.: Distributed cosegmentation via submodular optimization on anisotropic diffusion. In: IEEE ICCV, pp. 169–176 (2011)
Zhang, F.Q., Sun, Z.X., Song, M.F., Lang, X.F.: Progressive 3D shape segmentation using online learning. Comput. Aided Des. 58(1), 2–12 (2015)
Ristin, M., Guillaumin, M., Gall, J., Van Gool, L.: Incremental learning of NCM forests for large-scale image classification. In: IEEE CVPR, pp. 3654–3661 (2014)
Collins, R., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. In: IEEE TPAMI, pp. 1631–1643 (2005)
Saffari, A., Godec, M., Pock, T., et al.: Online multi-class LPBoost. In: IEEE CVPR, pp. 3570–3577 (2010)
Saffari, A., Leistner, C., Santner, J., et al.: Online random forests. In: IEEE ICCV Workshops, pp. 1393–1400 (2009)
Batra, D., Kowdle, A., et al.: Interactively co-segmentation topically related images with intelligent scribble guidance. Int. J. Comput. Vis. 93(3), 273–292 (2011)
Achanta, R., Shaji, A., Smith, K., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI 34(11), 2274–2282 (2012)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE TPAMI 23(11), 1222–1239 (2001)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. In: Eighth IEEE ICCV, pp. 105–112 (2001)
Acknowledgments
This work is supported by the National High Technology Research and Development Program of China (Project No. 2007AA01Z334), National Natural Science Foundation of China (Project No. 61321491 and 61272219), Innovation Fund of State Key Laboratory for Novel Software Technology (Project No. ZZKT2013A12).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hu, J., Sun, Z., Yang, K., Chen, Y. (2015). Progressive Image Segmentation Using Online Learning. In: Ho, YS., Sang, J., Ro, Y., Kim, J., Wu, F. (eds) Advances in Multimedia Information Processing -- PCM 2015. PCM 2015. Lecture Notes in Computer Science(), vol 9314. Springer, Cham. https://doi.org/10.1007/978-3-319-24075-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-24075-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24074-9
Online ISBN: 978-3-319-24075-6
eBook Packages: Computer ScienceComputer Science (R0)