Abstract
Interactive image segmentation scheme provides an opportunity to select/mark initial region(s) of the target object(s) with user interactions. In this way, the foreground objects are segmented easily and successfully from the scenes which have cluttered backgrounds and multiple objects. GrabCut technique that utilize graph theory, Gaussian Mixture Model and iterative energy minimization can be considered in this context. This study concentrate on the weakness that occur on the low-contrast images. Using a contrast enhancement technique as a preprocessing step in GrabCut is proposed to improve the segmentation performance. CLAHE, which is a successful adaptive contrast enhancement method is used with RGB color channels in this work. Experimental results show that the proposed approach gives much better results (4% accuracy improvement) than the original GrabCut method on the images sampled from the Caltech 256 image dataset.
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
Rother, C., Kolmogorov, V., Blake, A.: “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: International Conference on Computer Vision, pp. 105–112. IEEE Press, Vancouver (2001)
Shan, J., Tu, J., Lu, X., Yao, J., Li, L.: Optimal seamline detection for multiple image mosaicking via graph cuts. ISPRS J. Photogramm. Remote Sens. 113, 1–16 (2016)
Najjar, A., Gamra, S.B., Zagrouba, E.: Model-based graph-cut method for automatic flower segmentation with spatial constraints. Image Vis. Comput. 32, 1007–1020 (2014)
Han, S., Chen, Q., Sun, Q., Ji, Z., Wang, T.: Image segmentation based on weighting boundary information via graph cut. J. Vis. Commun. Image Represent. 33, 10–19 (2015)
Vaiapury, K., Aksay, A., Izquierdo, E.: GrabcutD: improved GrabCut using depth information. In: ACM International Conference on Multimedia, pp. 57–62. ACM Press, Firenze (2010)
Han, S., Tao, W., Wang, D., Tai, X.C., Wu, X.: Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor. IEEE Trans. Image Process. 18, 2289–2302 (2009)
Khattab, D., Ebied, H.M., Hussein, A.S., Tolba, M.F.: Multi-label automatic GrabCut for image segmentation. In: 14th International Conference on Hybrid Intelligent Systems, pp. 152–157. IEEE Press, Kuwait (2014)
Kim, K.S., Yoon, Y.J., Kang, M.C., Sun, J.Y., Ko, S.J.: An improved GrabCut using a saliency map. In: 3rd Global Conference on Consumer Electronics, pp. 317–318. IEEE, Tokyo (2014)
Khattab, D., Theobalt, C., Hussein, S.A., Tolba, F.M.: Modified GrabCut for human face segmentation. Ain Shams Eng. J. 5, 1083–1091 (2014)
Pizer, S.M., Amburn, E.P., Austin, J.D., Cromartie, R., Geselowitz, A., Greer, T., Romeny, B.H., Zimmerman, J.B., Zuiderveld, K.: Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 39, 335–368 (1987)
Gutierrez, J.E., Barrena, J.T., Aroca, P.R., Valls, A., Puig, D.: Interactive optic disk segmentation via discrete convexity shape knowledge using high-order functionals. In: International Conference of the Catalan Association for Artificial Intelligence, pp. 39–44. UPC, Barcelona (2016)
Okuboyejo, DA., Olugbara, OO., Odunaike, SA.: CLAHE inspired segmentation of dermoscopic images using mixture of methods. In: World Congress on Engineering and Computer Science (WCECS), pp. 355–365. IAENG Press, San Francisco (2013)
Hitam, M.S., Awalludin, E.A., Yussof, W.N., Bachok, Z.: Mixture contrast limited adaptive histogram equalization for underwater image enhancement. In: International Conference on Computer Applications Technology (ICCAT), pp. 1–5. IEEE Press, Sousse (2013)
Griffin, G., Holub, A., Perona, P.: The Caltech-256 Object Category Dataset. Technical report, Caltech (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Aykut, M., Akturk, S.M. (2018). An Improvement on GrabCut with CLAHE for the Segmentation of the Objects with Ambiguous Boundaries. In: Campilho, A., Karray, F., ter Haar Romeny, B. (eds) Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science(), vol 10882. Springer, Cham. https://doi.org/10.1007/978-3-319-93000-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-93000-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92999-6
Online ISBN: 978-3-319-93000-8
eBook Packages: Computer ScienceComputer Science (R0)