Computer vision aims to make computers mimic humans in order to understand their environments through visual interpretation. This book is a collection of 14 papers covering a wide range of problems in computer vision. Very notably, these papers are co-authored by both the best students that attended the yearly International Computer Vision Summer School (ICVSS) in recent years and some renowned researchers in the field.
The goal of this book is to provide an overview of recent works in computer vision. Among the different papers, readers will find some solutions enabling them to: identify important (for example, salient or redundant) features present in an image, automatically or from some user input; recognize the (static or dynamic) visual content, for example, objects, humans, or actions; reconstruct a 3D scene from 2D images; find correspondences between pairs of images (stereoscopy); provide a semantic label for an image from the analysis of very large annotated corpora; or even enhance data resolution.
Surprisingly, the book is a mix of survey papers and technical contributions. As such, it does not provide full and comprehensive coverage of the field, which could have been really helpful for beginners. The book is intended more for engineers and researchers who will use it as a relevant source of knowledge in the computer vision field, and benefit from the presence of recent and representative methods that are among the best existing solutions to solve the problems reviewed in the book.
This is yet another book in computer vision. Considering the long list of existing titles in the field, I do not find a convincing argument for deciding to pick this particular book off the shelf. Promoting the influence of doctoral studies on advances in computer vision is definitely a possible answer.