In 3D object detection and recognition, an object of interest is subject to changes in view as well as in illumination and shape. For image classification purpose, it is desirable to derive a representation in which intrinsic characteristics of the object are captured in a low dimensional space while effects due to artifacts are reduced. In this paper, we propose a method for view-based unsupervised learning of object appearances. First, view-subspaces are learned from a view-unlabeled data set of multi-view appearances, using independent subspace analysis (ISA). A learned view-subspace provides a representation of appearances at that view, regardless of illumination effect. A measure, called view-subspace activity, is calculated thereby to provide a metric for view-based classification. View-based clustering is then performed by using maximum view-subspace activity (MVSA) criterion. This work is to the best of our knowledge the first devoted research on view-based clustering of images.
View-based clustering of object appearances based on independent subspace analysis
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 295-300 vol.2
2001-01-01
889908 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
View-Based Clustering of Object Appearances Based on Independent Subspace Analysis
British Library Conference Proceedings | 2001
|Factorized appearances for object detection
British Library Online Contents | 2015
|Clustering Appearances of Objects under Varying Illumination Conditions
British Library Conference Proceedings | 2003
|Reweighted sparse subspace clustering
British Library Online Contents | 2015
|