initialization4LCKSVD(training_feats,H_train,dictsize,iterations,sparsitythres,tol=1e-4):

Initialization for Label consistent KSVD algorithm
Inputs
      training_feats  -training features
      H_train         -label matrix for training feature 
      dictsize        -number of dictionary items
      iterations      -iterations
      sparsitythres   -sparsity threshold
      tol             -tolerance when performing the approximate KSVD
Outputs
      Dinit           -initialized dictionary
      Tinit           -initialized linear transform matrix
      Winit           -initialized classifier parameters
      Q               -optimal code matrix for training features 

initialization4DKSVD(training_feats,labels,dictsize,iterations,sparsitythres,Dinit=None,tol=1e-4):

Initialization for Discriminative KSVD algorithm
Inputs
      training_feats  -training features
      labels          -label matrix for training feature (numberred from 1 to nb of classes)
      dictsize        -number of dictionary items
      iterations      -iterations
      sparsitythres   -sparsity threshold
      Dinit           -initial guess for dictionary
      tol             -tolerance when performing the approximate KSVD
Outputs
      Dinit           -initialized dictionary
      Winit           -initialized classifier parameters

labelconsistentksvd(Y,Dinit,labels,Winit,iterations,sparsitythres,sqrt_beta,sqrt_alpha=0.,Q_train=None,Tinit=None, tol=1e-4):

Label consistent KSVD algorithm
Inputs
      Y               -training features
      Dinit           -initialized dictionary
      labels          -labels matrix for training feature (numberred from 1 to nb of classes)
      Winit           -initialized classifier parameters
      iterations      -iterations for KSVD
      sparsitythres   -sparsity threshold for KSVD
      sqrt_beta       -contribution factor
      sqrt_alpha      -contribution factor (0. for D-KSVD)
      Q_train         -optimal code matrix for training feature (use only for LC-KSVD)
      Tinit           -initialized transform matrix (use only for LC-KSVD)
Outputs
      D               -learned dictionary
      X               -sparsed codes
      T               -learned transform matrix
      W               -learned classifier parameters

classification(D, W, data, sparsity):

Classification 
Inputs
      D               -learned dictionary
      W               -learned classifier parameters
      data            -data to classify
      sparsity        -sparsity threshold
outputs
      prediction      -predicted classification vectors. Perform sp.argmax(W.dot(gamma), axis=0) to get labels
      gamma           -learned representation