Title: Appearance Based Recognition of Complex Objects by Genetic Prototype-Learning
Authors: Stommel, Martin
Kuhnert, Klaus-Dieter
Citation: WSCG '2005: Short Papers: The 13-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2005 in co-operation with EUROGRAPHICS, p. 149-152.
Issue Date: 2005
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: http://wscg.zcu.cz/WSCG2005/Papers_2005/Short/!WSCG2005_Short_Proceedings_Final.pdf
ISBN: 80-903100-9-5
Keywords: rozpoznávání vzorců;rozhodovací stromy;genetický algoritmus
Keywords in different language: pattern recognition;decision trees;genetic algorithm
Abstract: This paper describes a method to recognize and classify complex objects in digital images. To this end, a uniform representation of prototypes is introduced. The notion of a prototype describes a set of local features which allow to recognize objects by their appearance. During a training step a genetic algorithm is applied to the prototypes to optimize them with regard to the classification task. After training the prototypes are compactly stored in a decision tree which allows a fast detection of matches between prototypes and images. The proposed method is tested with natural images of highway scenes, which were divided into 15 classes (including one class for rejection). The learning process is documented and the results show a classification rate of up to 93 percent for the training and test samples.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG '2005: Short Papers

Files in This Item:
File Description SizeFormat 
Stommel.pdfPlný text182,8 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/11231

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.