A Markov random field model-based approach to natural image matting
Pages 161 - 167
Abstract
This paper proposes a Markov Random Field (MRF) model-based approach to natural image matting with complex scenes. After the trimap for matting is given manually, the unknown region is roughly segmented into several joint sub-regions. In each sub-region, we partition the colors of neighboring background or foreground pixels into several clusters in RGB color space and assign matting label to each unknown pixel. All the labels are modelled as an MRF and the matting problem is then formulated as a maximum a posteriori (MAP) estimation problem. Simulated annealing is used to find the optimal MAP estimation. The better results can be obtained under the same user-interactions when images are complex. Results of natural image matting experiments performed on complex images using this approach are shown and compared in this paper.
References
[1]
Smith A R, Blinn J F. Blue screen matting. In Proc. SIGGRAPH 1996, New Orleans, USA, Aug. 1996, pp. 259-268.
[2]
Berman A, Vlahos P, Dadourian A. Comprehensive method for removing from an image the background surrounding a selected object. U.S. Patent 6,134,345, 2000.
[3]
Ruzon M, Tomasi C. Alpha estimation in natural images. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2000, Hilton Head Island, USA, June 2000, pp. 18-25.
[4]
Hillman P, Hannah J, Renshaw D. Alpha channel estimation in high resolution images and image sequences. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2001, Kauai, HI, USA, Dec. 2001, pp. 1063-1068.
[5]
Chuang Y Y, Curless B, Salesin D et al. A Bayesian approach to digital matting. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2001, Kauai, HI, USA, Dec. 2001, pp. 264-271.
[6]
Sun J, Jia J Y, Tang C K et al. Poisson matting. In Proc. SIGGRAPH 2004, Los Angeles, USA, Aug. 2004, pp. 315-321.
[7]
Qian R J, Sezan M I. Video background replacement without a blue screen. In Proc. The IEEE International Conference on Image Processing 1999, Kobe, Japan, Oct. 1999, pp. 143-146.
[8]
Geman S, Geman D. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE Trans. Pattern Analysis and Machine Intelligence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6(6): 721-741.
[9]
Cross G C, Jain A K. Markov random field texture models. IEEE Trans. Pattern Analysis and Machine Intelligence, IEEE Transactions on Pattern Analysis and Machine Intelligence , 1980, 5(1): 25-39.
[10]
Dubes R C, Jain A K. Random field models in image analysis. Journal of Applied Statistics, 1989, 16(2): 131-164.
[11]
Li S Z. Markov Random Field Modeling in Computer Vision. New York: Springer-Verlag, 1995, pp. 1-45.
[12]
Kirkpatrick S, Gellatt C D, Vecchi M P. Optimization by simulated annealing. Science, 1983, 220(4598): 671-680.
[13]
Orchard M T, Bouman C A. Color Quantization of Images. IEEE Trans. Signal Processing, 1991, 39(12): 2677-2690.
Index Terms
- A Markov random field model-based approach to natural image matting
Recommendations
MRF matting on complex images
MUSP'06: Proceedings of the 6th WSEAS international conference on Multimedia systems & signal processingThis paper proposes a novel approach to solve the matting problem on complex images using Markov Random Field (MRF) model. Although many natural image matting methods have been proposed, matting on complex images still remains as a challenge. Our ...
Technical section: Fast natural image matting in perceptual color space
This paper proposes a fast natural image matting method in perceptual color space. Natural image matting is usually composed of three steps: region segmenting, color estimating and alpha estimating. Our matting approach uses a practical model to ...
Image matting based on local color discrimination by SVM
Image matting is a technique used for extracting a foreground object in a static image by estimating the opacity, called alpha matte, at each pixel in the foreground image layer. The common drawback of the previous matting approaches is the decrease in ...
Comments
Information & Contributors
Information
Published In
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 January 2007
Revised: 04 September 2006
Received: 27 August 2004
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Jan 2025