IDRISI continues to provide high-level support for image classification. The most significant new development is the Neural Network Classifier that employs the back projection technique. Neural Network classifiers have been proven to provide superior results over parametric classifiers, such as Maximum Likelihood, whenever class reflectance distributions are not normal. Other new modules include canonical components analysis, a training site purifier to remove unrepresentative cases, a Mahalanobis distance classifier, and improvements to the existing unsupervised techniques.
The Kilimanjaro release also includes several high-level models of significant importance to resource managers and researchers. New routines include an implementation of the Revised Universal Soil Loss Equation (RUSLE) for modeling soil erosion, as well as the first Windows implementation of the GEOMOD predictive land change simulation model.
A series of major new import and export routines have been developed, including SPLUS support and enhanced Geotiff import and export. These are in addition to support for ERDAS Imagine IMG files and full support for HDF, incorporated last spring.
IDRISI, in its 18th year of continuous development, offers the most extensive analytical suite of any software system in the geoanalytical domain, particularly in the areas of decision support, uncertainty management, image processing and change and time series analysis. Built by researchers for researchers, IDRISI is a professional level tool that represents the outcome of one of the most extensive and sustained research and development efforts in the industry, firmly grounded within a non-profit philosophy.