A theory of shape identification

Abstract

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 retrieval, image mosaics, solid object recognition and video and web shape retrieval. More fundamentally, the ability of humans and animals to detect and recognize shapes is one of the enigmas of perception. Digital images and computer vision methods open new ways to address this enigma.

nbsp, Given a dictionary of digitized shapes and a previously unobserved digital image, the aim of shape recognition algorithms is to know whether some of the shapes in the dictionary are present in the image. This 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 the query shapes.