The book introduces the latest methods and algorithms developed in machine and deep learning (hybrid symbolic-numeric computations, robust statistical techniques for clustering and eliminating data as well as convolutional neural networks) dealing not only with images and the use of computers, but also their applications to visualization tasks generalized by up-to-date points of view. Associated algorithms are deposited on iCloud.
Computer vision (also known as machine vision; Jain et al., 1995), a multidisciplinary
field that is broadly a subfield of artificial intelligence and machine
learning has as one of its goals the extraction of useful information from images.
A basic problem in computer vision, therefore, is to try to understand, i.e., “see”
the structure of the real world from a given set of images through use of specialized
methods and general learning algorithms (e.g., Hartley and Zisserman 2003;
see Fig. 1). Its applications are well documented in Jähne and Haußecker (2000),
where it finds use e.g., in human motion capture (Moeslund and Granum 2001).
With the plethora of unmanned aircraft vehicles (UAVs) or drones (see Awange
2018; Awange and Kiema 2019), computer vision is stamping its authority in the
UAV field owing to its intelligent capability (Al-Kaff et al., 2018). Several publications
abound on computer vision, e.g., on algorithms for image processing
(e.g., Parker 2011, Al-Kaff et al., 2018), pattern recognition/languages in computer
vision (e.g., Chen 2015), feature extraction (Nixon and Aguado 2012) and