Image Matting using Superpixels Centroid
DOI:
https://doi.org/10.33317/ssurj.564Keywords:
Image matting, non- parametric, super-pixel, alpha matte, global and local samplesAbstract
The orientation and focus of this research piece is the extraction of foreground and compositing this extracted region onto a new background region. This phenomenon is termed as image matting, which is more utilized in film production or digital media world. The proposed method approaches the ill-posed nature of image matting via non-parametric sampling based method along with the clustering technique known as Superpixel. In the proposed method, pixels of entire image(s) are tends to gather in close proximity under one unit (Superpixel) with respect to color, intensity and texture. This gathering in close proximity reduces the search space more than 20 times and helps in efficiently finding association of unknown region with the samples from background and foreground. The use of samples facilitates the pixel color assimilating with local image structure, which is significant to calculate a good resultant alpha matte particularly in the image having complex textured and in natural images. To the best of my knowledge, the matting problem using centroids of Superpixels has not previously been explored. Results are evaluated on different images on online benchmark dataset for image matting. Results are comparable to the different matting algorithms applied independently on images of dataset. Result shows that the proposed approach significantly improves the results.
References
Rubin, M. (2006). Droidmaker: George Lucas and the digital revolution. Triad Publishing Company.
Porter, T., & Duff, T. (1984, January). Compositing digital images. In Proceedings of the 11th annual conference on Computer DOI: https://doi.org/10.1145/800031.808606
graphics and interactive techniques (pp. 253-259).
Li, X., Liu, K., & Dong, Y. (2018). Superpixel-Based Foreground Extraction With Fast Adaptive Trimaps. IEEE transactions on DOI: https://doi.org/10.1109/TCYB.2017.2747143
cybernetics, 48(9),2609–2619.
Yang, X., Qiao, Y., Chen, S., He, S., Yin, B., Zhang, Q., ... & Lau, R. W. (2020). Smart scribbles for image matting. ACM DOI: https://doi.org/10.1145/3408323
Transactions on Multimedia Computing, Communications, and Applications (TOMM), 16(4), 1-21.
Yao, G. (2017). A Survey on Pre-Processing in Image Matting. Journal of Computer Science and Technology, 32, 122-138.
Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., & Rott, P. (2009, June). A perceptually motivated online benchmark for DOI: https://doi.org/10.1109/CVPR.2009.5206503
image matting. In 2009 IEEE conference on computer vision and pattern recognition (pp. 1826-1833). IEEE.
Yao, G. (01 2017). A Survey on Pre-Processing in Image Matting. Journal of Computer Science and Technology, 32, 122–138. doi:10.1007/s11390-017-1709-z DOI: https://doi.org/10.1007/s11390-017-1709-z
Lin, F.J., & Chuang, J.H. (2018). Alpha Matting Using Robust Color Sampling and Fully Connected Conditional Random Fields. DOI: https://doi.org/10.1007/s11042-017-5031-0
Multimedia Tools Appl., 77(11), 14327–14342.
Sun, J., Jia, J., Tang, C.K., & Shum, H.Y. (2004). Poisson Matting. In ACM SIGGRAPH 2004 Papers (pp. 315–321). DOI: https://doi.org/10.1145/1186562.1015721
Grady, L., Schiwietz, T., Aharon, S., & Westermann, R. (2005, September). Random walks for interactive alpha-matting. In
Proceedings of VIIP (Vol. 2005, pp. 423-429). DOI: https://doi.org/10.3726/91467_423
Levin, A., Lischinski, D., & Weiss, Y. (2006). A Closed-Form Solution to Natural Image Matting. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 30, 228-242.
Chuang, Y. Y., Curless, B., Salesin, D. H., & Szeliski, R. (2001, December). A bayesian approach to digital matting. In Proceedings
of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (Vol. 2, pp. II-II).
IEEE.
Comaniciu, D., & Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on pattern DOI: https://doi.org/10.1109/34.1000236
analysis and machine intelligence, 24(5), 603-619.
Ruzon, M.A., & Tomasi, C. (2000). Alpha estimation in natural images. In Proceedings IEEE Conference on Computer Vision and
Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 1, 18-25 vol.1.
Wang, J., & Cohen, M..(2005) An iterative optimization approach for unified image segmentation and matting. . In ICCV, pages (pp. DOI: https://doi.org/10.1109/ICCV.2005.37
–943).
Wang, J., & Cohen, M. (2007). Optimized Color Sampling for Robust Matting. In CVPR. IEEE computer Society(pp. 1-8). DOI: https://doi.org/10.1109/CVPR.2007.383006
Rhemann, C., Rother, C., & Gelautz, M. (2008, September). Improving Color Modeling for Alpha Matting. In BMVC (Vol. 1, DOI: https://doi.org/10.5244/C.22.115
No. 2, p. 3).
Felzenszwalb, P., & Huttenlocher, D. (09 2004). Efficient Graph- Based Image Segmentation. International Journal of Computer
Vision, 59, 167–181.
He, K., Rhemann, C., Rother, C., Tang, X., & Sun, J. (2011, June). A global sampling method for alpha matting. In CVPR 2011 (pp. DOI: https://doi.org/10.1109/CVPR.2011.5995495
-2056). IEEE.
Mishima, Y. (1994). Soft edge chroma-key generation based upon hexoctahedral color space .U.S. Patent No. 5,355,174. Washington, DC: U.S. Patent and Trademark Office.
Gastal, E. S. L., & Oliveira, M. M. (2010). Shared Sampling for Real-Time Alpha Matting. Computer Graphics Forum, 29(2), 575– DOI: https://doi.org/10.1111/j.1467-8659.2009.01627.x
Feng, X., Liang, X., & Zhang, Z. (2016). A cluster sampling method for image matting via sparse coding. In Computer Vision–ECCV DOI: https://doi.org/10.1007/978-3-319-46475-6_13
: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 (pp. 204-219).
Springer International Publishing.
Cho, D., Tai, Y. W., & Kweon, I. S. (2019). Deep Convolutional Neural Network for Natural Image Matting Using Initial Alpha DOI: https://doi.org/10.1109/TIP.2018.2872925
Mattes. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 28(3), 1054–1067.
Lu, H., Dai, Y., Shen, C., & Xu, S. (2019). Indices matter: Learning to index for deep image matting. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3266-3275). DOI: https://doi.org/10.1109/ICCV.2019.00336
Qiao, Y., Liu, Y., Yang, X., Zhou, D., Xu, M., Zhang, Q., & Wei, X. (2020). Attention-guided hierarchical structure aggregation for DOI: https://doi.org/10.1109/CVPR42600.2020.01369
image matting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 13676-13685).
Levinshtein, A., Stere, A., Kutulakos, K. N., Fleet, D. J., Dickinson, S. J., & Siddiqi, K. (2009). TurboPixels: fast superpixels using
geometric flows. IEEE transactions on pattern analysis and machine intelligence, 31(12), 2290–2297.
Forte, M., & Pitié, F. (2020). $ F $, $ B $, Alpha Matting. arXiv preprint arXiv:2003.07711.
Liu, C., Ding, H., & Jiang, X. (2021). Towards enhancing fine- grained details for image matting. In Proceedings of the IEEE/CVF DOI: https://doi.org/10.1109/WACV48630.2021.00043
Winter Conference on Applications of Computer Vision (pp. 385- 393).
Kun Wang, Nanning Zheng, & Weixiang Liu (2005). Natural image matting with non-negative matrix factorization. In Proceedings of DOI: https://doi.org/10.1109/ICIP.2005.1530273
the 2005 International Conference on Image Processing, ICIP
, Genoa, Italy, September 11-14, 2005 (pp. 1186–1189). IEEE.
Shi, J., & Malik, J. (1997). Normalized cuts and image segmentation. In Proceedings of IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, 731-737.
Hao Wu, Yueli Li, Zhenjiang Miao, Yuqi Wang, Runsheng Zhu, Rongfang Bie, & Rui Lie (2016). A new sampling algorithm for
high-quality image matting. Journal of Visual Communication and Image Representation, 38, 573-581.
Tang, C. K., Li, D., & Chen, Q. (2012, June). KNN matting. In 2012 IEEE Conference on Computer Vision and Pattern Recognition (pp.
-876). IEEE Computer Society.
Dou Yan, & Xiao Feng, Kong Ling-Fu; Feng. (2009). Improved Knockout Natural Image Matting Algorithm. Computer
Engineering, 35(14), 212–214.
Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph- based image segmentation. International journal of computer DOI: https://doi.org/10.1023/B:VISI.0000022288.19776.77
vision, 59, 167-181.
Vedaldi, A., & Soatto, S. (2008). Quick shift and kernel methods for mode seeking. In Computer Vision–ECCV 2008: 10th European DOI: https://doi.org/10.1007/978-3-540-88693-8_52
Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part IV 10 (pp. 705-718). Springer Berlin
Heidelberg.
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). SLIC Superpixels Compared to State-of-the-Art
Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2282.
Yuanjie Zheng, & C. Kambhamettu (2009). Learning based digital matting. In 2009 IEEE 12th International Conference on Computer DOI: https://doi.org/10.1109/ICCV.2009.5459326
Vision, 889-896.
Assari, S. M., Idrees, H., & Shah, M. (2016). Re-identification of humans in crowds using personal, social and environmental
constraints. arXiv preprint arXiv:1612.02155.
Cai, S., Zhang, X., Fan, H., Huang, H., Liu, J., Liu, J., ... & Sun, J. (2019). Disentangled image matting. In Proceedings of the DOI: https://doi.org/10.1109/ICCV.2019.00891
IEEE/CVF International Conference on Computer Vision (pp. 8819-8828).
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2023 Anam Akbar, Aniqa Shirazi, Mohammad Sarim Farooqui (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.