Improving the classification of newborn EEG time-frequency representations using a combined time-frequency signal and image approach.
Boualem BoashashLarbi BoubchirGhasem AzemiPublished in: ISSPA (2012)
Keyphrases
- image classification
- signal processing
- image data
- image retrieval
- single image
- image features
- image analysis
- input image
- classification accuracy
- hyperspectral images
- frequency domain
- high resolution
- single channel
- feature extraction
- image content
- eeg signals
- preprocessing stage
- image representation
- spectral features
- support vector
- pattern recognition
- edge detection
- image regions
- low frequency
- feature vectors
- multiscale
- signal analysis
- compressive sensing
- thematic mapper
- spatial filters
- motor imagery
- image segmentation
- frequency band
- multiresolution
- extracted features
- pixel values
- image set
- feature space
- high frequency