A divide-and-conquer method for multi-net classifiers.
Dimitrios FrosyniotisAndreas StafylopatisAristidis LikasPublished in: Pattern Anal. Appl. (2003)
Keyphrases
- synthetic data
- detection method
- high precision
- classification method
- classification process
- significant improvement
- experimental evaluation
- high accuracy
- segmentation method
- machine learning
- classifier ensemble
- training samples
- decision tree classifiers
- classification algorithm
- detection algorithm
- feature set
- computational cost
- dynamic programming
- cost function
- prior knowledge
- k means
- objective function