Hypothesis-based image segmentation
| Preis: | 79.90 EUR* (inkl. MWST zzgl. Versand - Preis kann jetzt höher sein!) |
| Versand: | 0.00 EUR Versandkostenfrei innerhalb von Deutschland |
| Partner: | buecher.de |
| Hersteller: | Südwestdeutscher Verlag Für Hochschulschriften (Denecke, Alexander) |
| Stand: | 2015-08-04 03:50:33 |
Produktbeschreibung
This thesis addresses the ¿gure-ground segmentation problem in the context of complex systems for automatic object recognition. Firstly the problem of image segmentation in general terms is introduced, followed by a discussion about its importance for online and interactive acquisition of visual representations. Secondly a machine learning approach using arti¿cial neural networks is presented. This approach on the basis of Generalized Learning Vector Quantization is investigated in challenging scenarios such as the real-time ¿gure-ground segmentation of complex shaped objects under continuously changing environment conditions. The ability to ful¿ll these requirements characterize the novelty of the approach compared to state-of-the-art methods. Finally the proposed technique is extended in several aspects, which yields a framework for object segmentation that is applicable to improve current systems for visual object learning and recognition.
* Preis kann jetzt höher sein. Den aktuellen Stand und Informationen zu den Versandkosten finden sie auf der Homepage unseres Partners.
Folgende Produkte könnten dir ebenso gefallen
