Combining Gaussian Markov random fields with the discrete-wavelet transform for endoscopic image classification.
Michael HäfnerAlfred GanglMichael LiedlgruberAndreas UhlAndreas VécseiFriedrich WrbaPublished in: DPS (2009)
Keyphrases
- discrete wavelet transform
- image classification
- gaussian markov random fields
- wavelet domain
- multiresolution
- subband
- wavelet coefficients
- shift invariant
- dual tree
- image fusion
- high frequency
- image representation
- visual features
- haar wavelet transform
- wavelet transform
- low frequency
- dual tree complex wavelet transform
- complex wavelet transform
- bag of words
- non stationary
- feature vectors
- feature extraction
- fusion method
- laplacian pyramid
- sparse coding
- multiscale
- image features
- image processing
- frequency domain
- computational complexity
- maximum likelihood
- face recognition