Object Recognition Through Invariant Indexing
Charles A. RothwellBooks.org participates in affiliate programs including Bookshop.org and the Amazon Services LLC Associates Program. We may earn a commission from qualifying purchases made through links on this page, at no additional cost to you.
Overview
In Object Recognition through Invariant Indexing, Charles Rothwell provides a practical and accessible introduction to two-dimensional shape description using projective invariants while contrasting the various interpretations of the descriptors currently in use. He also surveys a number of new invariant descriptors for three-dimensional shapes that can be recovered from single images, showing how such measures can be used to ease the recognition of real objects by a computer. Rothwell then proceeds to describe a promising new architecture for a real recognition system. In reviewing a broad field of recognition theory, the book is unique in its deft synthesis of research and application. It will be welcomed by students and researchers in computer vision, robotics, pattern recognition, and image and signal processing.
"This research work fills a void in theoretical and practical studies of computer vision . . . .This work is valuable from both theoretical and practical points of view, and I would recommend it to readers interested in object recognition."--Computing Reviews
"Rothwell, a member of Project Robotvis at INRIA in France, has written a valuable book about object recognition, a central problem in computer (robot) vision."--Choice
Synopsis
In Object Recognition through Invariant Indexing, Charles Rothwell provides a practical and accessible introduction to two-dimensional shape description using projective invariants while contrasting the various interpretations of the descriptors currently in use. He also surveys a number of new invariant descriptors for three-dimensional shapes that can be recovered from single images, showing how such measures can be used to ease the recognition of real objects by a computer. Rothwell then proceeds to describe a promising new architecture for a real recognition system. In reviewing a broad field of recognition theory, the book is unique in its deft synthesis of research and application. It will be welcomed by students and researchers in computer vision, robotics, pattern recognition, and image and signal processing.