Abstract
This paper presents an effective algorithm, interactive 1-bit feedback segmentation using transductive inference (FSTI), that interactively reasons out image segmentation. In each round of interaction, FSTI queries the user one superpixel for acquiring 1-bit user feedback to define the label of that superpixel. The labeled superpixels collected so far are used to refine the segmentation and generate the next query. The key insight is treating the interactive segmentation as a transductive inference problem, and then suppressing the unnecessary queries via an intrinsic-graph-structure derived from transductive inference. The experiments conducted on five publicly available datasets show that selecting query superpixels concerning the intrinsic-graph-structure is helpful to improve the segmentation accuracy. In addition, an efficient boundary refinement is presented to improve segmentation quality by revising the misaligned boundaries of superpixels. The proposed FSTI algorithm provides a superior solution to the interactive image segmentation problem is evident.
Similar content being viewed by others
Notes
An online twenty questions game is available at [1].
Notice that the user does not need to specify any annotation location in interactive 1-bit feedback segmentation. For reference, the user in [37] has to specify the location and the label (region of interest) of one seed on the foreground object for figure–ground segmentation, and the user in [6] has to specify the location and the label (object class) of one seed per object for learning a semantic segmentation model.
The method is called ‘TQ’ since its interaction mechanism is similar to the twenty questions game.
The algorithm is called ‘EU’ since it based on the calculations of entropy and uncertainty.
The superpixel \(s_p\) with the highest entropy of \({\mathbf {t}}_p\) in Eq. (3) is selected as the initial query superpixel. Intuitively, the superpixel associated with the largest homogeneous region is selected.
The MR brain datasets and their manual segmentations are provided by the Center for Morphometric Analysis at Massachusetts General Hospital and are available at http://www.cma.mgh.harvard.edu/ibsr/.
The improvement in accuracy may be due to the property that the Laplacian matrix is normalized. The Laplacian matrices in the other two functions are not normalized.
References
20q.net. http://www.20q.net/
Achanta, R., Hemami, S.S., Estrada, F.J., Süsstrunk, S.: Frequency-tuned salient region detection. In: CVPR, pp. 1597–1604 (2009)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell. 16(6), 641–647 (1994)
Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: ICOSEG: interactive co-segmentation with intelligent scribble guidance. In: CVPR, pp. 3169–3176 (2010)
Bearman, A.L., Russakovsky, O., Ferrari, V., Li, F.: What’s the point: semantic segmentation with point supervision. In: ECCV, pp. 549–565 (2016)
Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV, pp. 105–112 (2001)
Carreira, J., Sminchisescu, C.: Constrained parametric min-cuts for automatic object segmentation. In: CVPR, pp. 3241–3248 (2010)
Chen, D., Chen, H., Chang, L.: Interactive segmentation from 1-bit feedback. In: ACCV, pp. 261–274 (2016)
Cheng, M., Prisacariu, V.A., Zheng, S., Torr, P.H.S., Rother, C.: Densecut: densely connected crfs for realtime grabcut. Comput. Graph. Forum 34(7), 193–201 (2015)
Dong, X., Shen, J., Shao, L., Yang, M.: Interactive cosegmentation using global and local energy optimization. IEEE Trans. Image Process. 24(11), 3966–3977 (2015)
Dubost, F., Peter, L., Rupprecht, C., Gutiérrez-Becker, B., Navab, N.: Hands-free segmentation of medical volumes via binary inputs. In: DLMIA, pp. 259–268 (2016)
Everingham, M., Gool, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Feng, J., Price, B., Cohen, S., Chang, S.: Interactive segmentation on rgbd images via cue selection. In: CVPR (2016)
Fowlkes, C.C., Martin, D.R., Malik, J.: Local figure-ground cues are valid for natural images. J. Vis. 7(8), 1–9 (2007)
Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: ICCV, pp. 1–8 (2009)
Grady, L.: Random walks for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1768–1783 (2006)
Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: CVPR, pp. 3129–3136 (2010)
He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397–1409 (2013)
Kass, M., Witkin, A.P., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(4), 321–331 (1988)
Kowdle, A., Chang, Y., Gallagher, A.C., Chen, T.: Active learning for piecewise planar 3d reconstruction. In: CVPR, pp. 929–936 (2011)
Küttel, D., Ferrari, V.: Figure-ground segmentation by transferring window masks. In: CVPR, pp. 558–565 (2012)
Li, H., Shen, C.: Interactive color image segmentation with linear programming. Mach. Vis. Appl. 21(4), 403–412 (2010)
Liu, T., Sun, J., Zheng, N., Tang, X., Shum, H.: Learning to detect a salient object. In: CVPR (2007)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Mortensen, E.N., Barrett, W.A.: Intelligent scissors for image composition. In: SIGGRAPH, pp. 191–198 (1995)
Rother, C., Kolmogorov, V., Blake, A.: "Grabcut": interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)
Rother, C., Minka, T.P., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching—incorporating a global constraint into mrfs. In: CVPR, pp. 993–1000 (2006)
Rupprecht, C., Peter, L., Navab, N.: Image segmentation in twenty questions. In: CVPR, pp. 3314–3322 (2015)
Stein, A.N., Stepleton, T.S., Hebert, M.: Towards unsupervised whole-object segmentation: combining automated matting with boundary detection. In: CVPR (2008)
Straehle, C.N., Köthe, U., Knott, G., Briggman, K.L., Denk, W., Hamprecht, F.A.: Seeded watershed cut uncertainty estimators for guided interactive segmentation. In: CVPR, pp. 765–772 (2012)
Vezhnevets, V., Konushin, V.: "Growcut"—interactive multi-label n-d image segmentation by cellular automata. In: GraphiCon (2005)
Vicente, S., Rother, C., Kolmogorov, V.: Object cosegmentation. In: CVPR, pp. 2217–2224 (2011)
Waggoner, J.W., Zhou, Y., Simmons, J.P., Graef, M.D., Wang, S.: Graph-cut based interactive segmentation of 3d materials-science images. Mach. Vis. Appl. 25(6), 1615–1629 (2014)
Wang, Q., Gao, J., Yuan, Y.: A joint convolutional neural networks and context transfer for street scenes labeling. IEEE Trans. Intell. Transp. Syst. http://ieeexplore.ieee.org/document/8012463/
Wang, Q., Gao, J., Yuan, Y.: Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Trans. Intell. Transp. Syst. 19(1), 230–241 (2018)
Wang, T., Han, B., Collomosse, J.P.: Touchcut: fast image and video segmentation using single-touch interaction. Comput. Vis. Image Underst. 120, 14–30 (2014)
Xu, C., Whitt, S., Corso, J.J.: Flattening supervoxel hierarchies by the uniform entropy slice. In: ICCV, pp. 2240–2247 (2013)
Xu, J., Collins, M.D., Singh, V.: Incorporating user interaction and topological constraints within contour completion via discrete calculus. In: CVPR, pp. 1886–1893 (2013)
Yan, C., Xie, H., Liu, S., Yin, J., Zhang, Y., Dai, Q.: Effective uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans. Intell. Transp. Syst. 19(1), 220–229 (2018)
Yan, C., Xie, H., Yang, D., Yin, J., Zhang, Y., Dai, Q.: Supervised hash coding with deep neural network for environment perception of intelligent vehicles. IEEE Trans. Intell. Transp. Syst. 19(1), 284–295 (2018)
Yan, C., Zhang, Y., Xu, J., Dai, F., Li, L., Dai, Q., Wu, F.: A highly parallel framework for HEVC coding unit partitioning tree decision on many-core processors. IEEE Signal Process. Lett. 21(5), 573–576 (2014)
Yan, C.C., Zhang, Y., Xu, J., Dai, F., Zhang, J., Dai, Q., Wu, F.: Efficient parallel framework for HEVC motion estimation on many-core processors. IEEE Trans. Circuits Syst. Video Technol. 24(12), 2077–2089 (2014)
Zhang, L., Peng, X., Li, G., Li, H.: A novel active contour model for image segmentation using local and global region-based information. Mach. Vis. Appl. 28(1–2), 75–89 (2017)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 6230–6239 (2017)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: NIPS, pp. 321–328 (2003)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chen, DJ., Chen, HT. & Chang, LW. Interactive 1-bit feedback segmentation using transductive inference. Machine Vision and Applications 29, 617–631 (2018). https://doi.org/10.1007/s00138-018-0923-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-018-0923-1