Classification of breast masses via nonlinear transformation of features based on a kernel matrix.
Tingting MuAsoke K. NandiRangaraj M. RangayyanPublished in: Medical Biol. Eng. Comput. (2007)
Keyphrases
- feature space
- kernel matrix
- mammogram images
- kernel principal component analysis
- feature vectors
- classification accuracy
- feature extraction
- feature set
- kernel methods
- kernel pca
- svm classifier
- class labels
- support vector machine
- training samples
- kernel learning
- input space
- machine learning
- kernel function
- feature subset
- digital mammograms
- breast cancer
- principal components
- principal component analysis
- image features
- support vector
- face recognition
- training process
- model selection
- variable selection
- low rank
- text classification
- image classification
- small number
- training set
- pattern recognition
- decision trees
- feature selection