Soft Segmentation Using Image Registration Based on Nonlocal Matting

Meidya Koeshardianto

Abstract


Soft segmentation is used for extracting foreground and background on image or video sequence. In this paper, we proposed a new method of soft extraction from an image or video using image registration based on nonlocal matting. One of the disadvantages in nonlocal matting is needed to obtain constraint manually. The constraint is used to identify foreground and background area on separate image region. Based on the registration method, we try to reduce the cost to determine it. First, a constraint is obtained with identify key points detection and descriptor between image source and template. Image template was provided before extracting. Then soft segmentation, nonlocal matting method, is used to extract region. In our experiment result, we show that our proposed framework has significant performance improvement over the state-of-the-art

Full Text:

PDF

References


N. M. Saad, N. S. M. Noor, A. R. Abdullah, S. Muda, A. F. Muda, and H. Musa, “Segmentation and classification analysis techniques for stroke based on diffusion weighted images,” IAENG

Int. J. Comput. Sci., vol. 44, no. 3, 2017.

M. Beneˇ, “Segmentation of MRI Images by Adaptive,” vol. i, no. July, 2015.

A. R. Smith and J. F. Blinn, “Blue screen matting,” SIGGRAPH ’96 Proc. 23rd Annu. Conf.

Comput. Graph. Interact. Tech., pp. 259–268, 1996.

T. Porter and T. Duff, “Compositing digital images,” ACM SIGGRAPH Comput. Graph., vol. 18, no. 3, pp. 253–259, 1984.

M. A. Ruzon and C. Tomasi, “Alpha Estimation in Natural Images,” Proc. CVPR, vol. 1, no. June,

pp. 18–25, 2000.

Chuang, Curless, Salesin, and Szeliski, “A Bayesian approach to digital matting,” Proc. 2001

IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. CVPR 2001, vol. 2, no. 3, p. II-264- II-271, 2001.

J. Sun, J. Jia, C. Tang, and H. Shum, “Poisson matting,” ACM Trans. Graph., vol. 23, no. 3, p.

, 2004.

L. Grady, T. Schiwietz, and S. Aharon, “Random walks for interactive alpha-matting,” IASTED Int. Conf. Vis. Imaging Image Process., pp. 423–429, 2005.

X. Bai and G. Sapiro, “Geodesic matting: A framework for fast interactive image and video segmentation and matting,” Int. J. Comput. Vis., vol. 82, no. 2, pp. 113–132, 2009.

A. Levin, D. Lischinski, and Y. Weiss, “A closed-form solution to natural image matting,” Pami, vol. 30, no. 2, pp. 228–42, 2008.

P. Lee and Y. Wu, “Nonlocal matting,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern

Recognit., pp. 2193–2200, 2011.

H. wang Liang Zang, Xiaomei He, “Shadow Verification Based on Feature Matching and Image

Matting,” Igarss 2014, no. 1, pp. 1–5, 2014.

K. Ahuja and P. Tuli, “Object Recognition by Template Matching Using Correlations and Phase

Angle Method,” Int. J. Adv. Res. …, vol. 2, no. 3, pp. 1368–1373, 2013.

L. Zhang, H. Wang, T. Deng, and X. He, “Improving integrality of detected moving objects based on image matting,” Chinese J. Electron., vol. 23, no. 4, pp. 742–746, 2014.

D. G. Lowe, “Distinctive image features from scale invariant keypoints,” Int’l J. Comput. Vis., vol. 60, pp. 91–11020042, 2004.


Refbacks

  • There are currently no refbacks.