Fast Fixed-point Algorithm for Image Segmentation
Funds:
The National Natural Science Foundation of China (11172314)
-
摘要: 該文在去除背景便能獲得目標的分割思想之上,提出了一個凸的無約束最小化問題。證明了問題提出過程中添加懲罰項的合理性,并通過實驗驗證了證明結(jié)果。在最小化求解方面,應(yīng)用次微分和近似算子的相關(guān)理論,構(gòu)造了求解的不動點算子,進而結(jié)合Opial -averaged定理,給出了求解所提凸優(yōu)化問題的不動點算法,并理論推導(dǎo)出了收斂條件,證明了算法的收斂性。與經(jīng)典文獻方法的對比實驗表明所提方法分割結(jié)果更精確。同時實驗顯示該文算法比梯度下降法和分裂Bregman方法更快速。另外,所提算法對初始曲線和噪聲有較好的魯棒性。
-
關(guān)鍵詞:
- 圖像處理 /
- 圖像分割 /
- 凸優(yōu)化問題 /
- 不動點算法
Abstract: Based on the idea that objects in a given image can be segmented by removing the background part, an unconstrained convex minimization problem is proposed. The penalization term added in the construction procedure of the proposed problem is proven to be viable, which is demonstrated by the experiment. At the computational level, a fixed-point operator and the corresponding algorithm are proposed by applying the theory of subdifferential and proximity operators, and Opial -averaged theorem. And then the convergence proof of the algorithm is given. Comparisons with other classical models show that the proposed segmentation model is more accurate. And the experiments also demonstrate that the fixed-point algorithm is faster than the gradient descent method and the split Bregman method. Moreover, the algorithm is robust to the initial curve and noise.-
Key words:
- Image processing /
- Image segmentation /
- Convex optimization /
- Fixed-point algorithm
-
Zhu W, Tai X, and Chan T. Image segmentation using Eulers Elastica as the regularization[J]. Journal of Scientific Computing, 2013, 15(2): 414-438. Yuan J, Bae E, Tai X, et al.. A spatially continuous max-flow and min-cut framework for binary labeling problems[J]. Numerische Mathmatik, 2014, 126(3): 559-587. 張澤均, 水鵬朗. 一種新的基于網(wǎng)格編碼和區(qū)域合并的SAR圖像快速分割算法[J]. 電子與信息學(xué)報, 2014, 36(4): 974-980. Zhang Ze-jun and Shui Peng-lang. A new fast SAR image segmentation algorithm based on grid coding and region merging[J]. Journal of Electronics Information Technology, 2014, 36(4): 974-980. 趙雪梅, 李玉, 趙泉華. 結(jié)合高斯回歸模型和隱馬爾可夫隨機場的模糊聚類圖像分割[J]. 電子與信息學(xué)報, 2014, 36(11): 2730-2736. Zhao Xue-mei, Li Yu, and Zhao Quan-hua. Image segmentation by fuzzy clustering algorithm combining hidden Markov random field and Gaussian regression model[J]. Journal of Electronics Information Technology, 2014, 36(11): 2730-2736. 李偉斌, 高二, 宋松和. 一種全局最小化的圖像分割方法[J]. 電子與信息學(xué)報, 2013, 35(4): 791-796. Li Wei-bin, Gao Er, and Song Song-he. A global minimization method for image segmentation[J]. Journal of Electronics Information Technology, 2013, 35(4): 791-796. Li Wei-bin, Song Song-he, and Luo Feng. Fast image segmentation by convex minimisation and split Bregman method[J]. Electronics Letters, 2013, 49(17): 1073-1074. Goldstein T and Osher S. The split Bregman method for 1 regularized problems[J]. SIAM Journal on Imaging Sciences, 2008, 2(2): 323-343. Micchelli C, Shen L, and Xu Y. Proximity algorithms for image models: denosing[J]. Inverse Problems, 2011, 27(4): 45009-45038. Osher S and Fedkiw R. Level Sset Methods and Dynamic Implicit Surfaces[M]. New York: Springer Verlag, 2002: 4-22. Bertsekas D. Nonlinear Programming[M]. Belmont: Athena Scientific, 2003: 209-210. Z?linescu C. Convex Analysis in General Vector Spaces[M]. River Edge: World Scientific, 2002: 79-88. Opial Z. Weak convergence of the sequence of successive approximations for nonexpansive mappings[J]. Bulletin American Mathematical Society, 1967, 73: 591-597. Chan T, Esedoglu S, and Nikolova M. Algorithms for finding global minimizers of image segmentation and denoising models[J]. SIAM Journal on Applied Mathematics, 2006, 66(5): 1632-1648. Bresson X, Esedoglu S, Vandergheynst P, et al.. Fast global minimization of the active contour/snake models[J]. Journal of Mathematical Imaging and Vision, 2007, 28(2): 151-167. Goldstein T, Bresson X, and Osher S. Geometric applications of the split Bregman method: segmentation and surface reconstruction[J]. SIAM Journal on Scientific Computing, 2010, 45(1-3): 272-293. Alpert S, Galun M, Basri R, et al.. Image segmentation by probabilistic bottom-up aggregation and cue integration[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007: 1-8. -
計量
- 文章訪問數(shù): 1334
- HTML全文瀏覽量: 170
- PDF下載量: 739
- 被引次數(shù): 0