A local Gaussian distribution fitting energy-based active contour model for image segmentation. (August 2018)

• Record Type: Journal Article
• Authors: Xu, Haiyong; Jiang, Gangyi; Yu, Mei; Luo, Ting
• Is Part Of: Computers & electrical engineering. Volume 70(2018)
• Page Start: 317
• Page End: 333
• Publication Date: 2018-08
• Subjects: Image segmentation -- Level set -- Gaussian distribution -- Bias field -- Intensity inhomogeneity; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.06.010
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Intensity inhomogeneity and the bias field often occur in real-world images, which cause considerable difficulties in image segmentation. This paper presents a local region-based active contour model for segmentation of images with intensity inhomogeneity and simultaneous estimation of the bias field. In our model, the local image intensities and the bias field are described by the Gaussian distributions with different means and variances. A local Gaussian distribution fitting energy functional is defined on the image region, which combines the level set function and the bias field. Then, gradient flow equations and the bias field are derived for energy minimization. Due to the definition of local image intensities and the bias field, the proposed model is able to deal with intensity inhomogeneity and estimate the bias field. Experimental results on real images demonstrate that the proposed model has advantages over the other classical methods.