A local region-based Chan–Vese model for image segmentation

• Published in: Pattern recognition Vol. 45; no. 7; pp. 2769 - 2779
• Main Authors: Liu, Shigang, Peng, Yali
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01-07-2012; Elsevier
• Subjects: Active contour model; Applied sciences; Computational efficiency; Evolution; Exact sciences and technology; Image processing; Image segmentation; Information, signal and communications theory; Level set; Mathematical models; Pattern recognition; Robustness; Segmentation; Shape; Signal processing; Telecommunications and information theory; Level set; Active contour model; Image segmentation; Performance evaluation; Heterogeneity; Gaussian filtering; Image processing; Robustness; Shape detection; Edge detection; Active contour
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2011.11.019

In this paper, a new region-based active contour model, namely local region-based Chan–Vese (LRCV) model, is proposed for image segmentation. By considering the image local characteristics, the proposed model can effectively and efficiently segment images with intensity inhomogeneity. To reduce the dependency on manual initialization in many active contour models and for an automatic segmentation, a degraded CV model is proposed, whose segmentation result can be taken as the initial contour of the LRCV model. In addition, we regularize the level set function by using Gaussian filtering to keep it smooth in the evolution process. Experimental results on synthetic and real images show the advantages of our method in terms of both effectiveness and robustness. Compared with the well-know local binary fitting (LBF) model, our method is much more computationally efficient and much less sensitive to the initial contour.
► A new region-based active contour model, namely local region-based Chan–Vese model, is proposed. ► The proposed model can effectively and efficiently segment images with intensity inhomogeneity. ► A degraded CV model is proposed, whose segmentation result can be taken as the initial contour of LRCV. ► We regularize the level set function by using Gaussian filtering to keep it smooth.