In this book Shimon Ullman focuses on the processes of high-level vision that deal with the interpretation and use of what is seen in the image. In particular, he examines two major problems. The first, object recognition and classification, involves recognizing objects despite large variations in appearance caused by changes in viewing position, illumination, occlusion, and object shape. The second, visual cognition, involves the extraction of shape properties and spatial relations in the course of performing visual tasks such as object manipulation, planning movements in the environment, or interpreting graphical material such as diagrams, graphs, and maps.
The book first takes up object recognition and develops a novel approach to the recognition of three-dimensional objects. It then studies a number of related issues in high-level vision, including object classification, scene segmentation, and visual cognition. Using computational considerations discussed throughout the book, along with psychophysical and biological data, the final chapter proposes a model for the general flow of information in the visual cortex.
Understanding vision is a key problem in the brain sciences, human cognition, and artificial intelligence. Because of the interdisciplinary nature of the theories developed in this work, High-Level Vision will be of interest to readers in all three of these fields.
This book uses the methodology of artificial intelligence to investigate the phenomena of visual motion perception: how the visual system constructs descriptions of the environment in terms of objects, their three-dimensional shape, and their motion through space, on the basis of the changing image that reaches the eye. The author has analyzed the computations performed in the course of visual motion analysis. Workable schemes able to perform certain tasks performed by the visual system have been constructed and used as vehicles for investigating the problems faced by the visual system and its methods for solving them.
Two major problems are treated: first, the correspondence problem, which concerns the identification of image elements that represent the same object at different times, thereby maintaining the perceptual identity of the object in motion or in change. The second problem is the three-dimensional interpretation of the changing image once a correspondence has been established.
The author's computational approach to visual theory makes the work unique, and it should be of interest to psychologists working in visual perception and readers interested in cognitive studies in general, as well as computer scientists interested in machine vision, theoretical neurophysiologists, and philosophers of science.