Automatic Spectral Rule-Based Preliminary Classification of Radiometrically Calibrated SPOT-4/-5/IRS, AVHRR/MSG, AATSR, IKONOS/QuickBird/OrbView/GeoEye, and DMC/SPOT-1/-2 Imagery - Part II: Classification Accuracy Assessment.
Andrea BaraldiLaurent DurieuxDario SimonettiGiulia ConcheddaFrancesco HoleczPalma BlondaPublished in: IEEE Trans. Geosci. Remote. Sens. (2010)
Keyphrases
- classification accuracy
- satellite imagery
- multispectral images
- training set
- feature space
- change detection
- remote sensing
- terms of classification accuracy
- feature selection
- hyperspectral data
- multispectral
- accurate classification
- improve the classification accuracy
- remote sensing images
- support vector
- hyperspectral images
- multi spectral images
- data driven
- satellite images
- spectral features
- pattern recognition
- naive bayes
- feature set
- thematic mapper
- classification algorithm
- training data
- high classification accuracy
- classification rate
- machine learning
- svm classification
- supervised classification
- data reduction
- supervised learning
- expert systems
- urban areas
- hyperspectral
- support vector machine svm
- text classification
- hyperspectral imagery
- semi supervised
- feature reduction
- face recognition
- image segmentation
- image processing
- neural network
- achieve high classification accuracy