Synopses & Reviews
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.
Table of Contents
1. The Visual Learning Problem,
K. Ikeuchi and M. Veloso2. MULTI-HASH: Learning Object Attributes and Hash Tables for Fast 3D Object Recognition, L. Grewe and A. Kak
3. Learning Control Strategies for Object Recognition, B.A. Draper
4. PADO: A New Learning Architecture for Object Recognition, A. Teller and M. Veloso
5. Learning Organization Hierarchies of Large Modelbases for Fast Recognition, K.L. Boyer and K. Sengupta
6. Application of Machine Learning in Function-Based Recognition, L. Stark et al.
7. Learning a Visual Model and an Image Processing Strategy from a Series of Silhouette Images on MIRACLE-IV, H. Matsubara, K. Sakaue and K. Yamamoto
8. Assembly Plan from Observation, K. Ikeuchi, T. Suehiro and S.B. Kang
9. Visual Event Perception, J.M. Siskind
10. A Knowledge Framework for Seeing and Learning, P.R. Cooper and M.A. Brand
11. Explanation Based Learning for Mobile Robot Perception, J. O'Sullivan, T.M. Mitchell and S. Thrun
12. Navigation with Landmarks: Computing Goal Locations from Place Codes, A. Redish and D.S. Touretzky