Active contours driven by local likelihood image fitting energy for image segmentation

Accurate image segmentation is an essential step in image analysis and understanding, where active contour models play an important part. Due to the noise, low contrast and intensity inhomogeneity in images, many segmentation algorithms suffer from limited accuracy. This paper presents a novel region-based active contour model for image segmentation by using the variational level set formulation. In this model, we construct the local likelihood image fitting (LLIF) energy functional by describing the neighboring intensities with local Gaussian distributions. The means and variances of local intensities in the LLIF energy functional are spatially varying functions, which can be iteratively estimated during an energy minimization process to guide the contour evolving toward object boundaries. To address diverse image segmentation needs, we also expand this model to the multiphase level set, multi-scale Gaussian kernels and narrowband formulations. The proposed model has been compared with several state-of-the-art active contour models on images with different modalities. Our results indicate that the proposed LLIF model achieves superior performance in image segmentation.