2003 | OriginalPaper | Buchkapitel
Summary and Conclusions
verfasst von : Sven Behnke
Erschienen in: Hierarchical Neural Networks for Image Interpretation
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In order to overcome limitations of current computer vision systems, this thesis proposed an architecture for image interpretation, called Neural Abstraction Pyramid. This hierarchical architecture consists of simple processing elements that interact with their neighbors. The recurrent interactions are described be weight templates.Weighted links form horizontal and vertical feedback loops that mediate contextual influences. Images are transformed into a sequence of representations that become increasingly abstract as their spatial resolution decreases, while feature diversity as well as invariance increase. This process works iteratively. If the interpretation of an image patch cannot be decided locally, the decision is deferred, until contextual evidence arrives that can be used as bias. Local ambiguities are resolved in this way.