Survey on Region Growing Segmentation and Classification for Hyperspectral Images

Abstract

Image processing of hyperspectral image sector shows a thriving upbeat in innovation of new and novel techniques. For obvious reasons, most of these apply to the process of image segmentation and classification, in which is the heart of image processing. Augmented use of hyperspectral images puts forth a hectic workload that needs to deal with spatial data imposing large memory and computing requirements. Thus, a paramount issue in image processing area is to design and implement segmentation and classification techniques demanding optimal resources. This paper presents a survey on all prominent region growing segmentation techniques analyzing each one and thus sorting out an optimal and promising technique.