Hierarchical Neural Networks for Image Interpretation

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.

• cognition
• computer vision
• control
• learning
• neural architectures
• neural network
• neural network learning
• neural networks
• object recognition
• pattern recognition
• perception
• performance
• supervised learning
• unsupervised learning
• visual perception
• algorithm analysis and problem complexity

From the reviews:

"This booklet is the reprint of a thesis. It addresses image interpretation using a neural network architecture mimicking the human visual system. … The exposition is divided in two parts, namely theory and applications. … In short this thesis is very interesting, well written and easy to read." (Jean Th. Lapresté, Zentralblatt MATH, Vol. 1041 (16), 2004)

• Computer Science Institute, University of Freiburg, Freiburg, Germany

  Sven Behnke

Policies and ethics