Skip navigation
Hardcover | Out of Print | 432 pp. | 8 x 10 in | July 1996 | ISBN: 9780262210133
Paperback | $8.75 Short | £7.95 | 432 pp. | 8 x 10 in | July 2000 | ISBN: 9780262710077
eBook | $27.00 Short | July 1996 | ISBN: 9780262324755

High-Level Vision

Object Recognition and Visual Cognition


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.

About the Author

Shimon Ullman is Samy and Ruth Cohn Professor of Computer Science at Weizmann Institute of Science, Rehovot, Israel.


“The book is not a review or textbook; it is more an idiosyncratic, personal history of Ullman's own thoughts and contributions to the field. But these contributions are so varied and important, and conveyed with such crystalline logic and precision, that the global view is inescapable.”
Anya Hurlbert, Nature
“In this book, Shimon Ullman makes clear the problems of visual object recognition and gives insights into possible solutions in the brain. Recommended reading for neuroscientists, psychologists, and engineers.”
Keiji Tanaka, Ph.D., RIKEN Institute
“Shimon Ullman's High-Level Vision presents a lucid and insightful picture of object recognition and visual cognition, written from a computational perspective. The reader acquires an excellent overview of the pertinent findings in psychophysics, neurophysiology, neuropsychology and machine vision as they bear upon high-level vision. but more imporantly, the work takes great care to lay out the key problems that must be addressed before our understanding in this area will be complete. In addition, Prof. Ullman also makes several important observations and distinctions about the process of seeing. Clearly this book will be of immense value to experimentalists, modellers, and engineers entering the field of vision, as well as those already expert in the field.”
Whitman Richards, Department of Brain & Cognitive Science, MIT
“This is the best book on high-level vision which I have ever read. It will have a strong influence on the vision community.”
Heinrich Bulthoff, Director, Max-Planck Institute for Biological Cybernetics
“This book marks a new era in the study of the more 'cognitive' aspects of vision. An interdisciplinary approach is used in a creative, careful, and rigorous way to produce deep insights into the nature of fundamental problems and their viable solutions. This book must be read by anyone interested in visual perception, natural or artificial.”
Stephen M. Kosslyn, Professor of Psychology, Harvard University