Early anomaly prediction in breast thermogram by hybrid model consisting of superpixel segmentation, sparse feature descriptors and extreme learning machine classifier.
Ritam SharmaJanki Ballabh SharmaRanjan MaheshwariDumitru BaleanuPublished in: Biomed. Signal Process. Control. (2021)
Keyphrases
- hybrid model
- extreme learning machine
- support vector regression
- feature descriptors
- support vector
- support vector machine
- support vector machine svm
- image regions
- image features
- feature points
- regression model
- image segmentation
- artificial neural networks
- kernel function
- level set
- segmentation method
- image matching
- local binary pattern
- shape descriptors
- feed forward neural networks
- feature space
- training data
- decision trees
- high dimensional
- energy function
- feature selection
- neural network
- shape features
- learning algorithm
- sparse representation
- feature set
- k nearest neighbor
- model selection
- feature vectors
- multiscale