Learning based on kernel discriminant-EM algorithm for image classification.
Qi TianJie YuYing WuThomas S. HuangPublished in: ICASSP (5) (2004)
Keyphrases
- em algorithm
- image classification
- expectation maximization
- mixture model
- maximum likelihood
- hidden variables
- gaussian mixture model
- parameter learning
- parameter estimation
- feature extraction
- generative model
- active learning
- maximum likelihood estimation
- learning algorithm
- expectation maximisation
- unsupervised learning
- supervised learning
- gaussian mixture
- feature space
- likelihood maximization
- penalized likelihood
- feature vectors
- probability density function
- hyperparameters
- likelihood function