Gesture Recognition

Principles, Techniques and Applications
Softcover Nachdruck of the original 1. Auflage 2018
ISBN: 978-3-319-87259-9
Verlag: Springer International Publishing

Buch, Englisch, Band 724, 276 Seiten, Previously published in hardcover, Format (B × H): 155 mm x 235 mm, Gewicht: 452 g

Reihe: Studies in Computational Intelligence

This book presents a thorough analysis of gestural data extracted from raw images and/or range data with an aim to recognize the gestures conveyed by the data. It covers image morphological analysis, type-2 fuzzy logic, neural networks and evolutionary computation for classification of gestural data. The application areas include the recognition of primitive postures in ballet/classical Indian dances, detection of pathological disorders from gestural data of elderly people, controlling motion of cars in gesture-driven gaming and gesture-commanded robot control for people with neuro-motor disability.

The book is unique in terms of its content, originality and lucid writing style. Primarily intended for graduate students and researchers in the field of electrical/computer engineering, the book will prove equally useful to computer hobbyists and professionals engaged in building firmware for human-computer interfaces. A prerequisite of high school level mathematics issufficient to understand most of the chapters in the book. A basic background in image processing, although not mandatory, would be an added advantage for certain sections.

Zielgruppe

Research

Autoren/Hrsg.

Saha, Sriparna

Konar, Amit

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Mensch-Maschine-Interaktion
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Mustererkennung, Biometrik

Inhaltsverzeichnis

Introduction.- Radon Transform based Automatic Posture Recognition in Ballet Dance.- Fuzzy Image Matching Based Posture Recognition in Ballet Dance.- Gesture Driven Fuzzy Interface System For Car Racing Game.- Type-2 Fuzzy Classifier based Pathological Disorder Recognition.- Probabilistic Neural Network based Dance Gesture Recognition.- Differential Evolution based Dance Composition.- EEG-Gesture based Artificial Limb Movement for Rehabilitative Applications.- Conclusions and Future Directions.- Index.