Ulteriori informazioni
Zusatztext This well-written monograph presents the author's research in object recognition through invariant indexing. This research work fills a void in theoretical and practical studies of computer vision. It can be used by researchers in computer object recognition and by implementors of object recognition systems. The length is just right. The presenation is clear. The index is adequate. All references are carefully selected and are cited in the text. This work is valuable from both theoretical and practical points of view, and I recommend it to readers interested in object recognition. Computing Reviews Klappentext 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. Zusammenfassung The problem of object recognition is central to computer vision in many applications such as the automatic sorting, selection, orientation, and inspection of manufactured items and in the navigation of mobile robots. This work addresses this area of robotics research. Inhaltsverzeichnis Introduction 1: Object recognition 2: Plane algebraic projective invariants 3: The recognition architecture: algebraic invariants: LEWIS1 4: Projective invariants of smooth plane curves: LEWIS2 5: Segmentation and grouping 6: Invariants for 3D objects Conclusions References Index ...
