Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-Based Invariant Image Feature Construction

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2008-05, Vol.19 (5), p.746-757
Main Authors: Huicheng Zheng, Lefebvre, G., Laurent, C.
Format: Article
Language:English
Subjects:
Adaptive-subspace self-organizing map (ASSOM)
adult image filtering
Algorithms
Applied sciences
Artificial Intelligence
Computer Science
Computer science
control theory
systems
Computer Vision and Pattern Recognition
Connectionism. Neural networks
Construction
Exact sciences and technology
feature construction
Filtering
Filters
Humans
Image classification
Image databases
Image Processing, Computer-Assisted - methods
Invariants
Learning
Linear Models
Machine Learning
Mathematical analysis
Muscles
Neural networks
Operators
Pattern recognition. Digital image processing. Computational geometry
Principal component analysis
Reproducibility of Results
Signal and Image Processing
Skin
Spatial databases
Studies
Sun
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/TNN.2007.911741