在影像處理中，影像分割被廣泛地使用於物體偵測、人臉辨識、機械視覺、醫學影像等應用，而主動輪廓模型是影像分割裡重要的基本工具。主動輪廓模型的基本框架為能量最小化樣條函數，在達到力平衡後，主動輪廓模型可以擷取出目標物體輪廓。然而，主動輪廓模型也有一些限制，像是不能處理圖形中的凹邊界以及距離邊緣太遠時則缺乏影像力作用，為了應用於各類影像，我們需要改善主動輪廓模型的表現。
一些改善的方法也已經被提出，但是只解決了部分問題，還有發展的空間。在本研究中，我們定義額外的能量項，稱其為壓力能，並將此壓力能加進能量最小化系統中，其能量項衍生力使輪廓有能力找出期望的解，壓力與內力之間的相互作用也使主動輪廓能更穩定地移動。與其他方法之間的比較指出壓力模型改善了主動輪廓的表現，最後的實驗結果都顯示我們的方法能穩定且有效地擷取物體邊界。

In image processing, image segmentation is used in application likes object detection, face recognition, machine vision, medical image. Active contour model, an
important base tool for image segmentation, is an energy-minimizing spline. After reaching force balance, active contour model extracts object outline. However, active
contour model has several drawbacks. It fails to detect concave boundaries and is not attracted to distant edges. For application to all kinds of images, we need to improve active contour model.
Several methods has also been proposed for active contour model, but they only partially resolved the problems. In this study, we define an another energy term called pressure energy and add this energy term to the system of energy minimization. The force derived from that energy term lets active contour model find the desired solution.
The interaction between pressure and internal force makes active contour model move stably. Compared with other methods indicates pressure model improve the performance of active contour model. Experiments show that our method can extract object boundaries efficiently and stably.

[1] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,”
INTERNATIONAL JOURNAL OF COMPUTER VISION, vol. 1, no. 4, pp. 321–
331, 1988.
[2] D. Marr and E. Hildreth, “Theory of edge detection,” Proceedings of the Royal
Society of London B: Biological Sciences, vol. 207, no. 1167, pp. 187–217, 1980.
[3] J. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern
Anal. Mach. Intell., vol. 8, pp. 679–698, June 1986.
[4] J. Chappelow, “Snakes: Active contour models,” 2005.
[5] R. Malladi, J. A. Sethian, and B. C. Vemuri, “Shape modeling with front propagation:
a level set approach,” IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 17, pp. 158–175, Feb 1995.
[6] V. Caselles, R. Kimmel, and G. Sapiro, “Geodesic active contours,” Int. J. Comput.
Vision, vol. 22, pp. 61–79, Feb. 1997.
[7] C. Xu and J. L. Prince, “Snakes, shapes, and gradient vector flow,” IEEE Transactions
on Image Processing, vol. 7, pp. 359–369, Mar 1998.
[8] R. Jain, R. Kasturi, and B. G. Schunck, Machine Vision, ch. 5, pp. 140–185.
New York, NY, USA: McGraw-Hill, Inc., 1995.
[9] R. O. Duda and P. E. Hart, “Use of the hough transformation to detect lines and
curves in pictures,” Commun. ACM, vol. 15, pp. 11–15, Jan. 1972.
64
[10] D. H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,”
Pattern Recognition, vol. 13, pp. 111–122, Jan. 1981.
[11] P. Fua and Y. G. Leclerc, “Model driven edge detection,” Machine Vision and
Applications, vol. 3, no. 1, pp. 45–56, 1990.
[12] A. A. Amini, S. Tehrani, and T. E. Weymouth, “Using dynamic programming
for minimizing the energy of active contours in the presence of hard constraints,”
in Computer Vision., Second International Conference on, pp. 95–99, Dec 1988.
[13] D. J. Williams and M. Shah, “A fast algorithm for active contours and curvature
estimation,” CVGIP: Image Underst., vol. 55, pp. 14–26, Jan. 1992.
[14] K. M. Lam and H. Yan, “Fast greedy algorithm for active contours,” Electronics
Letters, vol. 30, pp. 21–23, Jan. 1994.
[15] D. Cohen, “On active contour models and balloons,” in CVGIP Image, 1990.
[16] W.-P. Choi, K.-M. Lam, and W.-C. Siu, “An adaptive active contour model for
highly irregular boundaries,” Pattern Recognition, vol. 34, no. 2, pp. 323 – 331,
2001.