A provocative investigation of the future of photography and human perception in the age of AI. We are constantly photographing and being photographed while feeding machine learning databases with our data, which in turn is used to generate new images. Analyzing the transformation of photography by computation—and the transformation of human perception by algorithmically driven images, from CGI to AI—The Perception Machine investigates what it means for us to live surrounded by image flows and machine eyes. In an astute and engaging argument, Joanna Zylinska brings together media theory and neuroscience in a Vilém Flusser–Paul Virilio remix. Her “perception machine” names a technical universe of images and their infrastructures. But it also refers to a sociopolitical condition resulting from today’s automation of vision, imaging—and imagination. Written by a theorist-practitioner, the book incorporates Zylinska’s own art projects, some of which have been co-created with AI. The photographs, collages, films, and installations available as part of the book (and its companion website) provide a different mode of thinking about our technological futures, at a local as well as a planetary level. Offering provocative concepts such as eco-eco-punk, AUTO-FOTO-KINO, planetary micro-vision, loser images, and sensography, the book outlines an existential philosophy of messy media for a time when our practices of imaging and self-imaging are being radically redesigned. Importantly, it also offers a new vision of our future.

This unique book discusses machine understanding (MU). This new branch of classic machine perception research focuses on perception that leads to understanding and is based on the categories of sensory objects. In this approach the visual and non-visual knowledge, in the form of visual and non-visual concepts, is used in the complex reasoning process that leads to understanding. The book presents selected new concepts, such as perceptual transformations, within the machine understanding framework, and uses perceptual transformations to solve perceptual problems (visual intelligence tests) during understanding, where understanding is regarded as an ability to solve complex visual problems described in the authors’ previous books. Thanks to the uniqueness of the research topics covered, the book appeals to researchers from a wide range of disciplines, especially computer science, cognitive science and philosophy.

As perception stands for the acquisition of a real world representation by interaction with an environment, learning is the modification of this internal representation.This book highlights the relation between perception and learning and describes the influence of the learning in the interaction with the environment.Besides, this volume contains a series of applications of both machine learning and perception, where the former is often embedded in the latter and vice-versa.Among the topics covered, there are visual perception for autonomous robots, model generation of visual patterns, attentional reasoning, genetic approaches and various categories of neural networks.

The book provides an up-to-date on machine learning and visual perception, including decision tree, Bayesian learning, support vector machine, AdaBoost, object detection, compressive sensing, deep learning, and reinforcement learning. Both classic and novel algorithms are introduced. With abundant practical examples, it is an essential reference to students, lecturers, professionals, and any interested lay readers.

This book presents some of the most recent research results in the area of machine learning and robot perception. The chapters represent new ways of solving real-world problems. The book covers topics such as intelligent object detection, foveated vision systems, online learning paradigms, reinforcement learning for a mobile robot, object tracking and motion estimation, 3D model construction, computer vision system and user modelling using dialogue strategies. This book will appeal to researchers, senior undergraduate/postgraduate students, application engineers and scientists.

Keyword Spotting (KWS) has been proposed as a flexible and more error-tolerant alternative to full transcriptions. In most cases, it allows to retrieve arbitrary query words in handwritten historical document.This comprehensive compendium gives a self-contained preamble and visually attractive description to the field of graph-based KWS. The volume highlights a profound insight into each step of the whole KWS pipeline, viz. image preprocessing, graph representation and graph matching.Written by two world-renowned co-authors, this unique title combines two very current research fields of graph-based pattern recognition and document analysis. The book serves as an attractive teaching material for graduate students, as well as a useful reference text for professionals, academics and researchers.