Abstract
Traditional computer portrait caricature system mainly take the method that exaggerate and deform real images directly, that lead the facial image background also been deformed when exaggerate facial image. If in pretreatment stage, we segmented the characters and background of the input image, and then do the subsequent processing, the problem may be solved. But for better portrait caricature effects, we need an excellent segmentation algorithm. So, we propose an improved Grabcut image segmentation algorithm and use it to extract the prospect character image for exaggeration and deformation. In practical application, we separate deform and exaggerate the foreground characters image with TPS method, then fuse it with the original or new background picture, get the final image. Application proves, the method solves the background deformation problem well, and improves the quality and rate of image segmentation, caricature synthesis effect reality and natural.
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
Preview
Unable to display preview. Download preview PDF.
References
Boykov, Y., Jolly, M.-P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proc. IEEE Int. Conf. on Computer Vision, CD–ROM (2001)
Rother, C., Kolmogorov, V., Blake, A.: ” Grabcut”- Interactive Foreground Extraction using Iterated Graph Cuts
Chen, D., Chen, B., Mamic, G., et al.: Improved GrabCut segmentation via GMM optimization. In: Proc. of the 2008 International Conference on Digital Image Computing: Techniques and Applications. IEEE Computer Society, Washington, DC, pp. 39–45 (2008)
Liang-fen, Z., Jian-nong, H.: Improved image segmentation algorithm based on GrabCut. Journal of Computer Applications 33(1), 49–52 (2013)
Han, S.D., Tao, W.B., Wang, D.S., et al.: Image segmentation based on GrabCut framework integrating multi-scale nonlinear structure tensor. IEEE Trans. on Image Processing 18(10), 2289–2302 (2009)
Qiu-ping, X.: Target extraction method research based on graphcut theory. Shanxi Normal University (2009)
Yue-lan, X.: Superpixel-based Grabcut Color Image Segmentation. Computer Technology and Development 23(7), 48–51 (2013)
Jun-ming, W., Li-xin, G., Li, Z.: The research of Grab-Cut color image segmentation algorithm. TV Technology 32(6), 15–17 (2008)
Yu-jin, Z.: The transition zone and image segmentation. Chinese Journal of Electronics 24(1), 12–16 (1996)
Hong, D., Xiao-feng, Z.: Object abstraction algorithm with fast Grabcut. Computer Engineering and Design 33(4), 1477–1481 (2012)
Bookstein, F.L.: Principal warps: Thin-plate splines and the de-composition of deformation. Pattern Analysis and Machine Intelligence 11(6), 567–585 (1989)
Huang, H., Ma, X.W.: Frontal and Semi-Frontal Facial Caricature Synthesis Using Non-Negative Matrix Factorization. Journal of Computer Science and Technology 25(6), 1282–1292 (2010)
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
Li, S., Zheng, X., Chen, X., Zhan, Y. (2015). Portrait Image Segmentation Based on Improved Grabcut Algorithm. In: Tan, Y., Shi, Y., Buarque, F., Gelbukh, A., Das, S., Engelbrecht, A. (eds) Advances in Swarm and Computational Intelligence. ICSI 2015. Lecture Notes in Computer Science(), vol 9142. Springer, Cham. https://doi.org/10.1007/978-3-319-20469-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-20469-7_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20468-0
Online ISBN: 978-3-319-20469-7
eBook Packages: Computer ScienceComputer Science (R0)