Abstract
In this work, we propose a hybrid method for image segmentation based on the selection of four extreme points (leftmost, rightmost, top and bottom pixels at the object boundary), combining Deep Extreme Cut, a connectivity constraint for the extreme points, a marker-based color classifier from automatically estimated markers and a final relaxation procedure with the boundary polarity constraint, which is related to the extension of Random Walks to directed graphs as proposed by Singaraju et al. Its second constituent element presents theoretical contributions on how to optimally convert the 4 point boundary-based selection into connected region-based markers for image segmentation. The proposed method is able to correct imperfections from Deep Extreme Cut, leading to considerably improved results, in public datasets of natural images, with minimal user intervention (only four mouse clicks).
Thanks to CNPq (308985/2015-0, 313554/2018-8, 465446/2014-0), CAPES (88887.136422/2017-00) and FAPESP (2014/12236-1, 2014/50937-1, 2016/21591-5).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Circularity was measured by the isoperimetric quotient. That is, the ratio of the object area to the area of a circle with the same perimeter.
- 2.
The squared EDT values are quantized into 256 levels (8 bits) prior to the weighted mean computation.
- 3.
The sharpness measure is the complement of fuzziness as defined in [15].
- 4.
The source code is available on the website: http://www.vision.ime.usp.br/~pmiranda/downloads.html.
- 5.
The error rate is the percentage of misclassified pixels within the bounding boxes.
- 6.
The datasets are available on the website: http://www.vision.ime.usp.br/~pmiranda/downloads.html.
- 7.
References
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. Int. Conf. Comput. Vision (ICCV) 1, 105–112 (2001)
Bragantini, J., Martins, S.B., Castelo-Fernandez, C., Falcão, A.X.: Graph-based image segmentation using dynamic trees. In: Vera-Rodriguez, R., Fierrez, J., Morales, A. (eds.) CIARP 2018. LNCS, vol. 11401, pp. 470–478. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-13469-3_55
Cappabianco, F.A.M., Ribeiro, P.F.O., de Miranda, P.A.V., Udupa, J.K.: A general and balanced region-based metric for evaluating medical image segmentation algorithms. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1525–1529, September 2019. https://doi.org/10.1109/ICIP.2019.8803083
Ciesielski, K., Falcão, A., Miranda, P.: Path-value functions for which Dijkstra’s algorithm returns optimal mapping. J. Math. Imag. Vision 60(7), 1025–1036 (2018)
Demario, C.L., Miranda, P.A.V.: Relaxed oriented image foresting transform for seeded image segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1520–1524 (2019)
Dice, L.: Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
Falcão, A., Stolfi, J., Lotufo, R.: The image foresting transform: theory, algorithms, and applications. Trans. PAMI 26(1), 19–29 (2004)
Grady, L.: Random walks for image segmentation. Trans. PAMI 28(11), 1768–1783 (2006)
Gulshan, V., Rother, C., Criminisi, A., Blake, A., Zisserman, A.: Geodesic star convexity for interactive image segmentation. In: Proceedings of Computer Vision and Pattern Recognition, pp. 3129–3136 (2010)
Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: International Conference on Computer Vision (ICCV) (2011)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016. https://doi.org/10.1109/CVPR.2016.90
Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 277–284 (2009)
Malmberg, F., Nyström, I., Mehnert, A., Engstrom, C., Bengtsson, E.: Relaxed image foresting transforms for interactive volume image segmentation. In: Proceedings of SPIE, vol. 7623, pp. 7623–7623-11 (2010)
Maninis, K.K., Caelles, S., Pont-Tuset, J., Gool, L.V.: Deep extreme cut: from extreme points to object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 616–625 (2018)
Mansilla, L.A.C., Miranda, P.A.V.: Oriented image foresting transform segmentation: Connectivity constraints with adjustable width. In: 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 289–296, October 2016. https://doi.org/10.1109/SIBGRAPI.2016.047
Mansilla, L.A.C., Miranda, P.A.V., Cappabianco, F.A.M.: Oriented image foresting transform segmentation with connectivity constraints. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 2554–2558, September 2016
Mansilla, L., Miranda, P.: Image segmentation by oriented image foresting transform: handling ties and colored images. In: 18th International Conference on Digital Signal Processing, pp. 1–6. Santorini, GR, July 2013
Miranda, P., Falcão, A., Spina, T.: Riverbed: a novel user-steered image segmentation method based on optimum boundary tracking. IEEE Trans. Image Process. 21(6), 3042–3052 (2012)
Miranda, P., Falcão, A., Udupa, J.: Synergistic arc-weight estimation for interactive image segmentation using graphs. Comput. Vision Image Underst. 114(1), 85–99 (2010)
Miranda, P., Mansilla, L.: Oriented image foresting transform segmentation by seed competition. IEEE Trans. Image Process. 23(1), 389–398 (2014)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1520–1528 (2015)
Papadopoulos, D.P., Uijlings, J.R.R., Keller, F., Ferrari, V.: Extreme clicking for efficient object annotation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4940–4949 (2017)
Rother, C., Kolmogorov, V., Blake, A.: “grabcut’’: interactive foreground extraction using iterated graph cuts. ACM Trans. Gr. 23(3), 309–314 (2004)
Singaraju, D., Grady, L., Vidal, R.: Interactive image segmentation via minimization of quadratic energies on directed graphs. In: International Conference on Computer Vision and Pattern Recognition, pp. 1–8, June 2008
Tang, M., Ayed, I.B., Marin, D., Boykov, Y.: Secrets of grabcut and kernel k-means. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1555–1563 (2015)
Tang, M., Gorelick, L., Veksler, O., Boykov, Y.: Grabcut in one cut. In: 2013 IEEE International Conference on Computer Vision, pp. 1769–1776 (2013)
Wu, J., Zhao, Y., Zhu, J., Luo, S., Tu, Z.: Milcut: a sweeping line multiple instance learning paradigm for interactive image segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 256–263 (2014)
Xu, N., Price, B., Cohen, S., Yang, J., Huang, T.: Deep grabcut for object selection. In: Kim, T.-K., Stefanos Zafeiriou, G.B., Mikolajczyk, K. (eds.) Proceedings of the British Machine Vision Conference (BMVC), pp. 182.1-182.12. BMVA Press, September 2017
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Oliveira, D.E.C., Demario, C.L., Miranda, P.A.V. (2021). Image Segmentation by Relaxed Deep Extreme Cut with Connected Extreme Points. In: Lindblad, J., Malmberg, F., Sladoje, N. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2021. Lecture Notes in Computer Science(), vol 12708. Springer, Cham. https://doi.org/10.1007/978-3-030-76657-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-76657-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76656-6
Online ISBN: 978-3-030-76657-3
eBook Packages: Computer ScienceComputer Science (R0)