Esquemas morfológicos multiescala basados en operaciones de Top-Hat para aplicaciones de mejora y fusión de imágenes

Abstract

This thesis work presents applications of multiscale mathematical morphology to contrast enhancement of medical, infrared, visible images and its extension to visible and infrared image fusion techniques. The classical top-hat transform is a mathematical morphology operation that is used in contrast enhancement and image fusion processes. But this operation generates saturations in the image enhancement process especially at the edges of the images. Throughout this work, it is proposed to reduce the saturation effect in multiscale mathematical morphology based algorithms using different strategies in the Top-Hat transform. Furthermore, these variations were tested in new algorithms based on multiscale mathematical morphology applied to contrast enhancement of medical images, infrared images and visible images and in visible and infrared image fusion techniques. The results obtained show medical, infrared, visible and fused images with contrast enhancement, detail enhancement, brightness preservation and edge preservation.