Comparison of Local Higher-Order Moment Kernel and Conventional Kernels in SVM for Texture Classification.
Keisuke KameyamaPublished in: ICONIP (1) (2007)
Keyphrases
- texture classification
- kernel function
- higher order
- support vector
- kernel methods
- polynomial kernels
- multiple kernel learning
- local binary pattern
- rbf kernel
- texture analysis
- kernel parameters
- multiple kernel
- mercer kernel
- support vector machine
- svm classification
- feature space
- texture images
- texture features
- correct classification rate
- kernel machines
- gaussian kernel
- feature extraction
- rotation invariant
- string kernels
- reproducing kernel hilbert space
- kernel learning
- image analysis
- svm classifier
- support vector machine svm
- kernel matrix
- positive definite
- support vectors
- tree kernels
- gaussian kernels
- natural images
- linear svm
- feature selection
- machine learning
- spatial information
- linear combination
- natural textures
- brodatz textures
- standard svm
- optimal kernel
- histogram intersection kernel
- feature set
- knn
- pairwise
- multiscale
- kernel pca
- markov random field
- multiresolution
- feature vectors
- high dimensional
- video sequences
- training data
- computer vision