Some of the fundamental constraints of automated machine vision have been the inability to automatically adapt parameter settings or utilize previous adaptations in changing environments. Symbolic Visual Learning presents research which adds visual learning capabilities to computer vision systems. Using this state-of-the-art recognition technology, the outcome is different adaptive recognition systems that can measure their own performance, learn from their experience and outperform conventional static designs. Written as a companion volume to Early Visual Learning (edited by S. Nayar and T. Poggio), this book is intended for researchers and students in machine vision and machine learning.
1: K. Ikeuchi and M. Veloso: The Visual Learning Problem 2: L. Grewe and A. Kak: MULTI-HASH: Learning Object Attributes and Hash Tables for Fast 3D Object Recognition 3: B.A. Draper: Learning Control Strategies for Object Recognition 4: A. Teller and M. Veloso: PADO: A New Learning Architecture for Object Recognition 5: K.L. Boyer and K. Sengupta: Learning Organization Hierarchies of Large Modelbases for Fast Recognition 6: L. Stark et al.: Application of Machine Learning in Function-Based Recognition 7: H. Matsubara, K. Sakaue and K. Yamamoto: Learning a Visual Model and an Image Processing Strategy from a Series of Silhouette Images on MIRACLE-IV 8: K. Ikeuchi, T. Suehiro and S.B. Kang: Assembly Plan from Observation 9: J.M. Siskind: Visual Event Perception 10: P.R. Cooper and M.A. Brand: A Knowledge Framework for Seeing and Learning 11: J. O'Sullivan, T.M. Mitchell and S. Thrun: Explanation Based Learning for Mobile Robot Perception 12: A. Redish and D.S. Touretzky: Navigation with Landmarks: Computing Goal Locations from Place Codes