A Theory of Shape Identification
Buch in deiner Nähe kaufen
Beschreibung
Recent years have seen dramatic progress in shape recognition algorithms applied to ever-growing image databases. They have been applied to image stitching, stereo vision, image mosaics, solid object recognition and video or web image retrieval. More fundamentally, the ability of humans and animals to detect and recognize shapes is one of the enigmas of perception.
The book describes a complete method that starts from a query image and an image database and yields a list of the images in the database containing shapes present in the query image. A false alarm number is associated to each detection. Many experiments will show that familiar simple shapes or images can reliably be identified with false alarm numbers ranging from 10-5 to less than 10-300.
Technically speaking, there are two main issues. The first is extracting invariant shape descriptors from digital images. The second is deciding whether two shape descriptors are identifiable as the same shape or not. A perceptual principle, the Helmholtz principle, is the cornerstone of this decision.
These decisions rely on elementary stochastic geometry and compute a false alarm number. The lower this number, the more secure the identification. The description of the processes, the many experiments on digital images and the simple proofs of mathematical correctness are interlaced so as to make a reading accessible to various audiences, such as students, engineers, and researchers.
Recent years have seen dramatic progress in shape recognition algorithms applied to ever-growing image databases. They have been applied to image stitching, stereo vision, image mosaics, solid object recognition and video or web image retrieval. More fundamentally, the ability of humans and animals to detect and recognize shapes is one of the enigmas of perception. The book describes a complete method that starts from a query image and an image database and yields a list of the images in the database containing shapes present in the query image. A false alarm number is associated to each detection. Many experiments will show that familiar simple shapes or images can reliably be identified with false alarm numbers ranging from 10-5 to less than 10-300. Technically speaking, there are two main issues. The first is extracting invariant shape descriptors from digital images. Indeed, a shape can be seen from various angles and distances and in various lights.
Jean-Michel Morel belongs to the ISI list of highly cited mathematicians (http://isihighlycited.com/) The theory presented is new and original. The text aims at being self-contained in all three aspects: mathematics, vision and algorithms Specialists in image analysis and computer vision find the text easy on the computer vision side and affordable on the mathematical level. The mathematics students easily learn through the text itself what is needed in vision psychology and the practice of computer vision The prerequisites are elementary calculus and probability from the first two undergraduate years of any science course Includes supplementary material: sn.pub/extras
Autor*in
Frédéric Cao
Themen in »A Theory of Shape Identification«
Stereo a contrario methods algorithms calculus cluster analysis cognition databases meaningful level lines object recognition scale invariant features shape grouping shape recognition stereo vision