Special Issue on Fuzzy Logic for Image Processing

The increasing availability of huge image collections in different application fields, such as medical diagnosis, remote sensing, transmission and encoding, machine/robot vision, and video processing, microscopic imaging has pressed the need, in the last few last years, for the development of efficient techniques capable of managing and processing large collection of image data. In particular, techniques suitable for analysis, indexing and the retrieval of image data are of fundamental importance today. Classical image processing methods often face great difficulties while dealing with images containing noise and distortions. Under such conditions, fuzzy logic techniques turn out to be effective to address challenging real-world image processing problems that are often characterized by vagueness and uncertainty. The present Special Issue on Fuzzy Logic for Image Processing is intended to show the potential and the practical impacts of fuzzy logic techniques in challenging applications involving tasks required to understand, represent, and process digital images. The Special Issue received several submissions, all of which went through a rigorous peer-review process. After the review process, six papers have been selected on the basis of the review ratings and comments. These selected papers range over main applications of fuzzy logic in image processing, including image classification, image segmentation and edge detection. Classification of scenes, regions or objects within images is a fundamental task in many fields, especially related to image retrieval and remote sensing. In particular, scene classification in remote sensing images is an active research topic in the field of aerial and satellite image analysis, which aims to is to categorize images into a discrete set of meaningful classes according to the region types on the Earth’s surface. The first paper entitled “Land Cover Classification from Multispectral Data Using Computational Intelligence Tools: A Comparative Study” [1] addresses the problem of image fusion in land cover classification from multispectral satellite images. The authors propose a fuzzy fusion approach to fuse remote sensing spectral images into a higher level image of land cover distribution. When compared against other computational intelligence methods, this fuzzy approach demonstrates its suitability for spatio-temporal image fusion. Another essential and crucial task in image processing is segmentation, which consists of identifying homogeneous regions of interest in images for facilitating their characterization and further processing. Particularly, image segmentation is of fundamental importance in the field of medical imaging. For example, in Magnetic Resonance (MR) brain image analysis, segmentation is commonly used for detecting, measuring and analyzing the main anatomical structures of the brain and eventually identifying pathological regions. Among image segmentation methods, clustering-based approaches received a great interest in the domain of medical imaging and several fuzzy clustering algorithms have been proposed and accepted as effective tools for image segmentation. In our featured paper entitled “MR Brain Image Segmentation: A Framework to Compare Different Clustering Techniques” [2] we present a framework for image segmentation that includes different fuzzy clustering methods to perform the segmentation of MR images and enables easy comparison of different segmentation results by providing a quantitative evaluation using an entropy-based measure as well as other measures commonly used to evaluate segmentation results. In the paper “Automated Prostate Gland Segmentation Based on an Unsupervised Fuzzy C-Means Clustering Technique Using Multispectral