Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper, we present a method for subspace learning, which takes these considerations into account. We present an incremental method, which sequentially updates the principal subspace considering weighted influence of individual images as well as individual pixels within an image. This approach is further extended to enable determination of consistencies in the input data and imputation of the values in inconsistent pixels using the previously acquired knowledge, resulting in a novel incremental, weighted and robust method for subspace learning.
Weighted and robust incremental method for subspace learning
Proceedings Ninth IEEE International Conference on Computer Vision ; 1494-1501 vol.2
2003-01-01
673763 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Weighted and Robust Incremental Method for Subspace Learning
British Library Conference Proceedings | 2003
|Incremental and robust learning of subspace representations
British Library Online Contents | 2008
|A Framework for Robust Subspace Learning
British Library Online Contents | 2003
|A Framework for Robust Subspace Learning
British Library Online Contents | 2003
|Incremental Learning for Robust Visual Tracking
British Library Online Contents | 2008
|