A Biased Vector Field Convolution External Force for Snakes

详细信息    查看全文

• 作者：Guoqi Liu (1)
  Zhiheng Zhou (1)
  Shengli Xie (2)
  
• 关键词：Active contour model ; Vector field ; Vector field convolution ; Image聽segmentation
• 刊名：Circuits, Systems, and Signal Processing
• 出版年：2014
• 出版时间：April 2014
• 年：2014
• 卷：33
• 期：4
• 页码：1299-1312
• 全文大小：1,472 KB
• 参考文献：1. S. Alpert, M. Galun, R. Basri, A. Brandt, Image segmentation by probabilistic bottom-up aggregation and cue integration, in / Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (2007), pp. 1鈥?
  2. G. Aubert, P. Kornprobst, / Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations (Springer, New York, 2006)
  3. V. Caselles, F. Catte, T. Coll, F. Dibos, A geometric model for active contours. Numer. Math. 66, 1鈥?1 (1993) CrossRef
  4. L. Cohen, I. Cohen, Finite-element methods for active contour models and balloons for 2D and 3D images. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1131鈥?147 (1993) CrossRef
  5. M. Kass, A. Witkin, D. Terzopoulus, Snakes: active contour model. Int. J. Comput. Vis. 1(4), 321鈥?31 (1988) CrossRef
  6. R. Kimmel, A. Amir, A. Bruckstein, Finding shortest paths on surfaces using level set propagation. IEEE Trans. Pattern Anal. Mach. Intell. 17(6), 635鈥?40 (1995) CrossRef
  7. A. Kovacs, T. Sziranyi, Harris function based active contour external force for image segmentation. Pattern Recognit. Lett. 33, 1180鈥?187 (2012) CrossRef
  8. B. Li, S.T. Acton, Active contour external force using vector field convolution for image segmentation. IEEE Trans. Image Process. 16(8), 2096鈥?106 (2007) CrossRef
  9. J.F. Ning, C.K. Wu, S.G. Liu, S.Q. Yang, NGVF: an improved external force field for active contour model. Pattern Recognit. Lett. 28, 58鈥?3 (2007) CrossRef
  10. L.M. Qin, C. Zhu, Y. Zhao, H.H. Bai, H.W. Tian, Generalized gradient vector flow for snakes: new observations, analysis, and improvement. IEEE Trans. Circuits Syst. Video Technol. 23(5), 883鈥?97 (2013) CrossRef
  11. T. Wang, I. Cheng, A. Basu, Fluid vector flow and applications in brain tumor segmentation. IEEE Trans. Biomed. Eng. 56(3), 781鈥?89 (2009) CrossRef
  12. Y.Q. Wang, L.X. Liu, H. Zhang, Z.L. Cao, S.P. Lu, Image segmentation using active contours with normally biased GVF external force. IEEE Signal Process. Lett. 17(10), 875鈥?78 (2010) CrossRef
  13. S.L. Xie, D.L. Zeng, Z.H. Zhou, J. Zhang, Arranging and interpolating sparse unorganized feature points with geodesic circular arc. IEEE Trans. Image Process. 18(3), 582鈥?95 (2009) CrossRef
  14. C.Y. Xu, J. Prince, Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process. 7(3), 359鈥?69 (1998) CrossRef
  15. C.Y. Xu, J. Prince, Generalized gradient vector flow external forces for active contours. Signal Process. 71(2), 131鈥?39 (1998) CrossRef
  16. G.P. Zhu, S.Q. Zhang, Q.S. Zeng, C.H. Wang, Gradient vector flow active contours with prior directional information. Pattern Recognit. Lett. 31, 845鈥?56 (2010) CrossRef
  
• 作者单位：Guoqi Liu (1)
  Zhiheng Zhou (1)
  Shengli Xie (2)
  
  1. School of Electronic and Information Engineering, South China University of Technology, GuangZhou, 510641, China
  2. School of Automation, Guangdong University of Technology, GuangZhou, 510006, China
  
• ISSN：1531-5878

文摘

The vector field convolution (VFC) is an effective external force for active contour models. However, it always comes across premature convergence in extracting complex geometries, especially narrow and deep concavity when the initial contour is set outside of the object boundary. In this letter, a biased vector field convolution (BVFC) external force is proposed. In BVFC, an indicator function with respect to the contour and a narrow band are introduced to biasedly utilize the edges gradient information of a concave region. On the other hand, a feature map which better describes the principal curvatures and equally emphasizes both corners and edges is also introduced. Experimental results demonstrate that the BVFC snake improves the performance in extracting object boundary and shows the ability to converge to concavity compared with several state-of-art active contour models.