Although linear representations of images are widely used in appearance-based recognition of objects, the frequently used ideas, such as PCA, ICA, and FDA, are often found to be suboptimal. A stochastic search algorithm has been proposed recently [4] for finding representations that are optimal for specific tasks and datasets. However, this search algorithm is computationally efficient only when the image size is relatively small. Here we propose a hierarchical learning algorithm to speed up the search. The proposed approach decomposes the original optimization problem into several stages according to a hierarchical organization. In particular, the following idea is applied recursively: (i) reduce the image dimension using a shrinkage matrix, (ii) optimize the recognition performance in the reduced space, and (iii)expand the optimal subspace to the bigger space in a pre-specified way. We show that the optimal performance is maintained in the last step. By applying this decomposition procedure recursively, a hierarchy of layers is formed. This speeds up the original algorithm significantly since the search is performed mainly in reduced spaces. The effectiveness of hierarchical learning is illustrated on a popular database, where the computation time is reduced by a large factor compared to the original algorithm.
Statistical Search for Hierarchical Linear Optimal Representations of Images
01.06.2003
261797 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Optimal Linear Representations of Images for Object Recognition
British Library Conference Proceedings | 2003
|Optimal Threshold Selection in Hierarchical Coders for Images and Video
British Library Conference Proceedings | 1994
|Refining action segmentation with hierarchical video representations
Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021
|