In this book, Shimon Ullman focuses on the processes of high-level vision that dealwith the interpretation and use of what is seen in the image. In particular, he examines two majorproblems. The first, object recognition and classification, involves recognizing objects despitelarge variations in appearance caused by changes in viewing position, illumination, occlusion, andobject shape. The second, visual cognition, involves the extraction of shape properties and spatialrelations in the course of performing visual tasks such as object manipulation, planning movementsin the environment, or interpreting graphical material such as diagrams, graphs and maps.The bookfirst takes up object recognition and develops a novel approach to the recognition ofthree-dimensional objects. It then studies a number of related issues in high-level vision,including object classification, scene segmentation, and visual cognition. Using computationalconsiderations discussed throughout the book, along with psychophysical and biological data, thefinal chapter proposes a model for the general flow of information in the visualcortex.Understanding vision is a key problem in the brain sciences, human cognition, and artificialintelligence. 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.
Shimon Ullman is Samy and Ruth Cohn Professor of Computer Science at Weizmann Institute of Science, Rehovot, Israel.