A Comparative Evaluation of Polarimetric Distance Measures within the Random Forest Framework for the Classification of Polsar Images.
Ronny HänschOlaf HellwichPublished in: IGARSS (2018)
Keyphrases
- comparative evaluation
- random forest
- distance measure
- image classification
- decision trees
- similarity measure
- nearest neighbor classification
- feature set
- object recognition
- distance function
- feature vectors
- ensemble classifier
- random forests
- vector space
- euclidean distance
- image features
- dynamic time warping
- nearest neighbor classifier
- feature selection
- class labels
- classification accuracy
- support vector
- machine learning
- multi label
- training samples
- support vector machine
- angular error
- decision tree learning algorithms