Region-based image segmentation has essentially been solved by the Chan-Vese (CV) model. However, this model fails when images are affected by artifacts (outliers) and illumination bias that outweigh the actual image contrast. Here, we implement a model for segmenting such images. In a single energy functional, we introduce 1) a dynamic artifact class preventing intensity outliers from skewing the segmentation, and 2), in Retinex-fashion, we decompose the image into a piecewise-constant structural part and a smooth bias part. The CV-segmentation terms then only act on the structure, and only in regions not identified as artifacts. The segmentation is parameterized using a phase-field, and efficiently minimized using threshold dynamics.
For a complete description of the theory and algorithm, see our paper "Image Segmentation with Dynamic Artifacts Detection and Bias Correction" by D. Zosso, J. An, J. Stevick, N. Takaki, M. Weiss, L. S. Slaughter, H. H. Cao, P. S. Weiss and A. L. Bertozzi, submitted to AIMS Inverse Problems and Imaging. Preprint available at: ftp://ftp.math.ucla.edu/pub/camreport/cam15-07.pdf