With the recent rapid progress on deep convolutional neural networks, deep learning has achieved remarkable performance in various felds.In particular, it has brought a revolution to the computer vision community, introducing non-traditional and effcient solutions to several problems that had long remained unsolved. Due to this promising performance, it is gaining more and more attention and is being applied widely in computer vision for several tasks such as object detection and recognition, object segmentation, pedestrian detection, aerial imagery registration, video processing, scene classifcation, autonomous driving, and robot localization as well as medical imagerelated applications. If the phrase “deep learning for computer vision” is searched in Google, millions of search results will be obtained. Under these circumstances, a book entitled Deep Learning in Computer Vision that covers recent progress and achievements in utilizing deep learning for computer vision tasks will be extremely useful.
The purpose of this contributed volume is to fll the existing gap in the literature
for the applications of deep learning in computer vision and to provide a bird’s eye
view of recent state-of-the-art models designed for practical problems in computer
vision. The book presents a collection of eleven high-quality chapters written by
renowned experts in the feld. Each chapter provides the principles and fundamentals
of a specifc topic, introduces reviews of up-to-date techniques, presents outcomes,
and points out challenges and future directions. In each chapter, fgures, tables,
and examples are used to improve the presentation and analysis of covered topics.
Furthermore, bibliographic references are included in each chapter, providing a good
starting point for deeper research and further exploration of the topics considered in
this book.