Name
Title | ||
|---|---|---|
Fast-learning adaptive-subspace self-organizing map: an application to saliency-based invariant image feature construction. |
Abstract | ||
|---|---|---|
The adaptive-subspace self-organizing map (ASSOM) is useful for invariant feature generation and visualization. However, the learning procedure of the ASSOM is slow. In this paper, two fast implementations of the ASSOM are proposed to boost ASSOM learning based on insightful discussions of the basis rotation operator of ASSOM. We investigate the objective function approximately maximized by the classical rotation operator. We then explore a sequence of two schemes to apply the proposed ASSOM implementations to saliency-based invariant feature construction for image classification. In the first scheme, a cumulative activity map computed from a single ASSOM is used as descriptor of the input image. In the second scheme, we use one ASSOM for each image category and a joint cumulative activity map is calculated as the descriptor. Both schemes are evaluated on a subset of the Corel photo database with ten classes. The multi-ASSOM scheme is favored. It is also applied to adult image filtering and shows promising results. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/TNN.2007.911741 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
multi-assom scheme,adaptive-subspace self-organizing map,saliency-based invariant image,proposed assom implementation,image category,fast-learning adaptive-subspace self-organizing map,basis rotation operator,input image,image classification,single assom,adult image,feature construction,joint cumulative activity map,principal component analysis,artificial intelligence,objective function,filtering,algorithms,helium,skin,sun,image features,linear models,visualization,cumulant | Salience (neuroscience),Computer science,Image processing,Self-organizing map,Artificial intelligence,Artificial neural network,Contextual image classification,Computer vision,Subspace topology,Pattern recognition,Filter (signal processing),Invariant (mathematics),Machine learning | Journal |
Volume | Issue | ISSN |
19 | 5 | 1045-9227 |
Citations | PageRank | References |
11 | 0.69 | 29 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Huicheng Zheng | 1 | 125 | 21.37 |
| Gregoire Lefebvre | 2 | 82 | 12.13 |
| Christophe Laurent | 3 | 13 | 1.06 |