Hypothesis-based image segmentation for object learning and recognition
Denecke A (2010)
Bielefeld: Universität Bielefeld.
Bielefelder E-Dissertation | Englisch
Download
Autor*in
Gutachter*in / Betreuer*in
Steil, Jochen
Abstract / Bemerkung
This thesis addresses the figure-ground segmentation problem in the context of complex systems for automatic object recognition as well as for the online and interactive acquisition of visual representations. First the problem of image segmentation in general terms and next its importance for object learning in current state-of-the-art systems is introduced. Secondly a method using artificial neural networks is presented. This approach on the basis of Generalized Learning Vector Quantization is investigated in challenging scenarios such as the real-time figure-ground segmentation of complex shaped objects under continuously changing environment conditions. The ability to fulfill these requirements characterizes the novelty of the approach compared to state-of-the-art methods.
Finally our technique is extended towards online adaption of model complexity and the integration of several segmentation cues. This yields a framework for object segmentation that is applicable to improve current systems for visual object learning and recognition.
Jahr
2010
Seite(n)
179
Page URI
https://pub.uni-bielefeld.de/record/2486114
Zitieren
Denecke A. Hypothesis-based image segmentation for object learning and recognition. Bielefeld: Universität Bielefeld; 2010.
Denecke, A. (2010). Hypothesis-based image segmentation for object learning and recognition. Bielefeld: Universität Bielefeld.
Denecke, Alexander. 2010. Hypothesis-based image segmentation for object learning and recognition. Bielefeld: Universität Bielefeld.
Denecke, A. (2010). Hypothesis-based image segmentation for object learning and recognition. Bielefeld: Universität Bielefeld.
Denecke, A., 2010. Hypothesis-based image segmentation for object learning and recognition, Bielefeld: Universität Bielefeld.
A. Denecke, Hypothesis-based image segmentation for object learning and recognition, Bielefeld: Universität Bielefeld, 2010.
Denecke, A.: Hypothesis-based image segmentation for object learning and recognition. Universität Bielefeld, Bielefeld (2010).
Denecke, Alexander. Hypothesis-based image segmentation for object learning and recognition. Bielefeld: Universität Bielefeld, 2010.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Name
Access Level
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Zuletzt Hochgeladen
2019-09-06T09:18:00Z
MD5 Prüfsumme
bc43ac2045633218b3d2c420742b2b4e