Automated Diagnosis of Brain Tumours Using a Novel Density Estimation Method for Image Segmentation and Independent Component Analysis Combined with Support Vector Machines for Image Classification.
Dimitris GlotsosPanagiota SpyridonosPanagiota RavazoulaDionisis A. CavourasGeorge NikiforidisPublished in: ICONIP (2004)
Keyphrases
- independent component analysis
- density estimation
- brain tumours
- method for image segmentation
- image classification
- magnetic resonance
- mixture model
- factor analysis
- magnetic resonance spectroscopy
- principal component analysis
- density function
- level set
- probability density
- signal processing
- probability density function
- outlier detection
- feature extraction
- parzen window
- em algorithm
- blind source separation
- gaussian mixture model
- mr images
- medical images
- edge detection
- segmentation method
- sparse representation
- svm classifier
- computer vision
- expectation maximization
- higher order
- image features
- probabilistic model
- pairwise
- face recognition
- image segmentation