Human performance in visual perception by far exceeds the performance of contemporary computer vision systems. While humans are able to perceive their environment almost instantly and reliably under a wide range of conditions, computer vision systems work well only under controlled conditions in limited domains.
This book sets out to reproduce the robustness and speed of human perception by proposing a hierarchical neural network architecture for iterative image interpretation. The proposed architecture can be trained using unsupervised and supervised learning techniques.
Applications of the proposed architecture are illustrated using small networks. Furthermore, several larger networks were trained to perform various nontrivial computer vision tasks.
Author(s): Sven Behnke (auth.)
Series: Lecture Notes in Computer Science 2766
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2003
Language: English
Pages: 227
City: Berlin; New York
Tags: Computation by Abstract Devices; Neurosciences; Algorithm Analysis and Problem Complexity; Artificial Intelligence (incl. Robotics); Image Processing and Computer Vision; Pattern Recognition
Front Matter....Pages -
Introduction....Pages 1-13
Front Matter....Pages 15-15
Neurobiological Background....Pages 17-33
Related Work....Pages 35-63
Neural Abstraction Pyramid Architecture....Pages 65-94
Unsupervised Learning....Pages 95-110
Supervised Learning....Pages 111-126
Front Matter....Pages 127-127
Recognition of Meter Values....Pages 129-147
Binarization of Matrix Codes....Pages 149-165
Learning Iterative Image Reconstruction....Pages 167-190
Face Localization....Pages 191-202
Summary and Conclusions....Pages 203-207
Back Matter....Pages -
