Discriminative, Competitive, and Collaborative Representation-Based Classification with -Norm Regularizations

Algorithm 1

The proposed DCCRC method.

Input: The given training set and testing sample y with three regularized parameters , , and .
Output: Determine the class label of y.
(1)	Normalize each sample of X and y.
(2)	Calculate and G with equation (11).
(3)	Solve the representation vector with equation (17).
(4)	Calculate the class-specific representation residuals with .
(5)	Predict the label of y with equation (18).