×

Image segmentation by relaxed deep extreme cut with connected extreme points. (English) Zbl 1484.68301

Lindblad, Joakim (ed.) et al., Discrete geometry and mathematical morphology. First international joint conference, DGMM 2021, Uppsala, Sweden, May 24–27, 2021. Proceedings. Cham: Springer. Lect. Notes Comput. Sci. 12708, 441-453 (2021).
Summary: 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).
For the entire collection see [Zbl 1476.68014].

MSC:

68U10 Computing methodologies for image processing
68R10 Graph theory (including graph drawing) in computer science
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Boykov, Y.; Veksler, O.; Zabih, R., Fast approximate energy minimization via graph cuts, IEEE Trans. Pattern Anal. Mach. Intell., 23, 11, 1222-1239 (2001) · doi:10.1109/34.969114
[2] Boykov, Y.; Jolly, MP, Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images, Int. Conf. Comput. Vision (ICCV), 1, 105-112 (2001) · doi:10.1109/ICCV.2001.937505
[3] Bragantini, J.; Martins, SB; Castelo-Fernandez, C.; Falcão, AX; Vera-Rodriguez, R.; Fierrez, J.; Morales, A., Graph-based image segmentation using dynamic trees, Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 470-478 (2019), Cham: Springer, Cham · doi:10.1007/978-3-030-13469-3_55
[4] 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. doi:10.1109/ICIP.2019.8803083
[5] 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) · Zbl 1397.05187 · doi:10.1007/s10851-018-0793-1
[6] 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)
[7] Dice, L., Measures of the amount of ecologic association between species, Ecology, 26, 297-302 (1945) · doi:10.2307/1932409
[8] 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
[9] Falcão, A.; Stolfi, J.; Lotufo, R., The image foresting transform: theory, algorithms, and applications, Trans. PAMI, 26, 1, 19-29 (2004) · doi:10.1109/TPAMI.2004.1261076
[10] Grady, L., Random walks for image segmentation, Trans. PAMI, 28, 11, 1768-1783 (2006) · doi:10.1109/TPAMI.2006.233
[11] 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)
[12] Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: International Conference on Computer Vision (ICCV) (2011)
[13] 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. doi:10.1109/CVPR.2016.90
[14] 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)
[15] 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)
[16] 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)
[17] 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. doi:10.1109/SIBGRAPI.2016.047
[18] 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
[19] 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
[20] 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) · Zbl 1373.94285 · doi:10.1109/TIP.2012.2188034
[21] 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) · doi:10.1016/j.cviu.2009.08.001
[22] Miranda, P.; Mansilla, L., Oriented image foresting transform segmentation by seed competition, IEEE Trans. Image Process., 23, 1, 389-398 (2014) · Zbl 1374.94261 · doi:10.1109/TIP.2013.2288867
[23] 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)
[24] 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)
[25] Rother, C.; Kolmogorov, V.; Blake, A., “grabcut”: interactive foreground extraction using iterated graph cuts, ACM Trans. Gr., 23, 3, 309-314 (2004) · doi:10.1145/1015706.1015720
[26] 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
[27] 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)
[28] Tang, M., Gorelick, L., Veksler, O., Boykov, Y.: Grabcut in one cut. In: 2013 IEEE International Conference on Computer Vision, pp. 1769-1776 (2013)
[29] 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)
[30] 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
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.