Equivalence of some common linear feature extraction techniques for appearance-based object recognition tasks.
other
Where this comes from
- Record sourced from PubMed, PMID 17356208.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Recently, a number of empirical studies have compared the performance of PCA and ICA as feature extraction methods in appearance-based object recognition systems, with mixed and seemingly contradictory results. In this paper, we briefly describe the connection between the two methods and argue that whitened PCA may yield identical results to ICA in some cases. Furthermore, we describe the specific situations in which ICA might significantly improve on PCA.
Medical subject headings
- Algorithms
- Artificial Intelligence
- Image Enhancement
- Image Interpretation, Computer-Assisted
- Linear Models
- Pattern Recognition, Automated