Linear sparse feature based face detection in gray images

A very simple algorithm is used to construct an over complete set of linear sparse feature based classifiers, and AdaBoost algorithm is adopted to select part of them to form a strong classifier. During the course of feature extraction and selection, the new method minimizes the classification error directly, whereas most previous works cannot do this. An important difference between this method and other methods is that the sparse features are learned from the training set, instead of being arbitrarily defined. Experiments demonstrate that the new algorithm performs quite well.