Hierarchical Neural Networks for Image Interpretation

Sven Behnke

ISBN 10: 3540407227 / ISBN 13: 9783540407225

Editore: Springer Berlin Heidelberg, 2003

Riguardo questo articolo

Druck auf Anfrage Neuware - Printed after ordering - 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 booksets 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.

Codice articolo 9783540407225

Dati bibliografici

• Titolo: Hierarchical Neural Networks for Image Interpretation
• Editore: Springer Berlin Heidelberg
• Data di pubblicazione: 2003
• Lingua: Inglese
• ISBN 10: 3540407227
• ISBN 13: 9783540407225
• Rilegatura: Taschenbuch
• Condizione: Neu
• Dimensioni: 235 L x 155 A x 14 P (millimetri) 235 millimetri di larghezza per 155 millimetri di altezza per 14 millimetri di profondità
• Peso: 371 grammi

Descrizione articolo

Riassunto

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.

Recensione

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)