Improved level set model based on bias information with application to color image segmentation and correction

Compared with gray images, color images provide richer information stored in different channels, which increases the segmentation complexity. In this paper, we integrate the level set method, the split Bregman method with the illumination and reflectance estimation (IRE) model to propose an improved level set model. With the bias field added, the proposed model can jointly segment color images and correct the intensity inhomogeneity by removing the estimated bias fields. The energy functional is given with the level set formulation, which is made up of the weighted length term and the data fitting term. The split Bregman method is employed to minimize the energy functional with special form, so that the algorithm efficiency is significantly improved. Various types of color medical and natural images are segmented and corrected by the proposed model. Experimental results demonstrate that our model has a satisfactory application in segmenting and correcting color images. Comparison results with the IRE model validate that our model is superior to the IRE model in terms of segmentation and correction. Research on parameter sensitivity illustrates that our model is not sensitive to most parameters such that the parameters can be chosen flexibly. Besides, our model is robust to noises and initial contours.