A Machine Learning Pipeline to Analyse Multispectral and Hyperspectral Images

Machine Learning is a branch of Artificial Intelligence with the goal of learning patterns from data. These techniques fall into two big categories: supervised and unsupervised learning. The former classify data based on a given set of examples whose classification is known (hence the name supervised), while the latter try to group the data without knowing a priori the possible classes. Neural Networks and clustering algorithms are two of the most prominent examples of the two aforementioned categories. In this paper, we describe a machine learning pipeline to analyse multispectral and hyperspectral images. Our approach first adopts neural networks to identify relevant pixels and then applies a clustering algorithm to group the pixels according to two different criteria, namely intensity and variation of intensity.