Examining convolutional feature extraction using Maximum Entropy (ME) and Signal-to-Noise Ratio (SNR) for image classification.
Nidhi GowdraRoopak SinhaStephen G. MacDonellPublished in: IECON (2020)
Keyphrases
- signal to noise ratio
- maximum entropy
- image classification
- feature extraction
- sparse coding
- noise reduction
- maximum entropy principle
- feature vectors
- conditional random fields
- edge detection
- minimum cross entropy
- principle of maximum entropy
- feature space
- image features
- transformation based learning
- bit error rate
- face recognition
- principal component analysis
- sparse representation
- gaussian noise
- matched filter
- wavelet transform
- feature selection
- class specific
- minimum mean square error
- machine learning
- received signal
- wiener filter
- pairwise
- prior knowledge
- frequency domain