Back to Search
Start Over
Unsupervised Alignment of Image Manifolds with Centrality Measures
- Source :
- ICPR, Proceedings-International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., Proceedings-International Conference on Pattern Recognition
- Publication Year :
- 2014
- Publisher :
- IEEE, 2014.
-
Abstract
- The re use of available labeled samples to classify newly acquired data is a hot topic in pattern analysis and machine learning. Classification or regression algorithms developed with data from one domain cannot be directly used in another related domain unless the data representation or the classifier have been adapted to the new data distribution. This is crucial in satellite/airborne image analysis: when confronted to domain shifts issued from changes in acquisition or illumination conditions image classifiers tend to become inaccurate. In this paper we introduce a method to align data manifolds that represent the same land cover classes but have undergone spectral distortions. The proposed method relies on a recently proposed semi supervised manifold alignment technique. We propose an algorithm to relax the strong requirement of labeled data in all domains by exploiting centrality measures over graphs to match the manifolds. Experiments on multispectral pixel classification at very high spatial resolution show the potential of the method.
- Subjects :
- Power graph analysis
Manifold alignment
business.industry
Multispectral image
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Graph analysis
Pattern recognition
Remote sensing
15. Life on land
External Data Representation
Very high resolution
Statistical classification
ComputingMethodologies_PATTERNRECOGNITION
Centrality measures
Computer vision
Artificial intelligence
business
Centrality
Classifier (UML)
Image resolution
Mathematics
Subjects
Details
- ISBN :
- 978-1-4799-5208-3
- ISBNs :
- 9781479952083
- Database :
- OpenAIRE
- Journal :
- 2014 22nd International Conference on Pattern Recognition
- Accession number :
- edsair.doi.dedup.....7371d89af7dfc2657ebf94ca0b84cc0b
- Full Text :
- https://doi.org/10.1109/icpr.2014.167