A Selective Fuzzy Region Competition Model for Multiphase Image Segmentation

This paper presents a multiphase image segmentation model based on Fuzzy Region Competition. The proposed model approximates image regions by probability density functions and uses a supervised approach in the segmentation process. The strategy of the proposed model is to perform two-phase Fuzzy Region Competition model several times, where a hard partition is obtained in each round from the determined fuzzy membership function. Consequently, the segmentation process is soft, while the final result is hard, given the simplicity of avoiding non-overlapping and vacuum regions. The proposed model was validated using multiphase images, which showed to be robust under the presence of noise and presented good accuracy when dealing with texturized and natural images.