We introduce a novel method for constructing and selecting scale-invariant object parts. Scale-invariant local descriptors are first grouped into basic parts. A classifier is then learned for each of these parts, and feature selection is used to determine the most discriminative ones. This approach allows robust pan detection, and it is invariant under scale changes-that is, neither the training images nor the test images have to be normalized. The proposed method is evaluated in car detection tasks with significant variations in viewing conditions, and promising results are demonstrated. Different local regions, classifiers and feature selection methods are quantitatively compared. Our evaluation shows that local invariant descriptors are an appropriate representation for object classes such as cars, and it underlines the importance of feature selection.
Selection of scale-invariant parts for object class recognition
01.01.2003
1611915 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Selection of Scale-Invariant Parts for Object Class Recognition
British Library Conference Proceedings | 2003
|Object Class Recognition by Unsupervised Scale-Invariant Learning
British Library Conference Proceedings | 2003
|Scale-Invariant Shape Features for Recognition of Object Categories
British Library Conference Proceedings | 2004
|