Evolving Cellular Automata to Segment Hyperspectral Images Using Low Dimensional Images for Training

This paper describes a hyperspectral image segmentation approach that has been developed to address the issues of lack of adequately labeled images, the computational load induced when using hyperspectral images in training and, especially, the adaptation of the level of segmentation to the desires of the users. The algorithm used is based on evolving cellular automata where the fitness is established based on the use of synthetic RGB images that are constructed on-line according to a set of parameters that define the type of segmentation the user wants. A series of segmentation experiments over real hyperspectral images are presented to show this adaptability and how the performance of the algorithm improves over other state of the art approaches found in the literature on the subject.