This book illustrates how to deal with complex media and convert raw data into useful information. Once the original data have been converted into a digital representation, the processing of different media can be performed under the unifying framework of machine learning. Therefore only part of the information extraction processes is media specific and most work can be made by applying general techniques valid for a wide range of problems. Apparently very different domains like face verification and text categorization become, from a processing point of view, equivalent. Organized into 3 parts: The 1st focuses on technical aspects, basic mathematical notions and elementary machine learning techniques. The 2nd provides an extensive survey of most relevant machine learning techniques for media processing. The 3rd focuses on applications and shows how techniques are applied in actual problems. This unique book offers an introduction and advanced material in the combined fields of machine learning and image/video processing.