Level set method with Retinex‐corrected saliency embedded for image segmentation

It can be a very challenging task when using level set method segmenting natural images with high intensity inhomogeneity and complex background scenes. A new synthesis for robust image segmentation based on the combination of Retinex-corrected saliency region information edge is proposed in this work. First, Retinex theory introduced to correct extraction. Second, embedded into due its advantageous quality which makes foreground object stand out relative backgrounds. Combined information, boundary will more precise smooth. Experiments indicate that algorithm efficient, fast, reliable, robust.