Introduction to 1-D discrete-time signals and systems, frequency domain representation, filtering, prediction, parameter estimation.
Image basics, frequency domain representation, image enhancement and restoration (histogram equalization, spatial filtering, median filtering, Weiner filtering), extension to multispectral images (e.g. RGB), Image compression, edge detection.
Pattern Recognition. a) Classification: problem definition, (optimal) Bayes classifier, linear and nonlinear suboptimal classifiers, feature generation (extraction, selection). b) Clustering: Problem definition, clustering algorithms and clustering validation.
Hyperspectral image (HSI) processing. Basic definitions, HSI processing techniques: spectral unmixing, classification/clustering.