2D-PCA representation and sparse representation for image recognition

The two-dimensional principal component analysis (2D-PCA) method has been widely applied in fields of image classification, computer vision, signal processing and pattern recognition. The 2DPCA algorithm also has a satisfactory performance in both theoretical research and real-world applications. It not only retains main information of the original face images, but also decreases the dimension of original face images. In this paper, we integrate the 2D-PCA and spare representation classification (SRC) method to distinguish face images, which has great performance in face recognition. The novel representation of original face image obtained using 2D-PCA is complementary with original face image, so that the fusion of them can obviously improve the accuracy of face recognition. This is also attributed to the fact the features obtained using 2D-PCA are usually more robust than original face image matrices. The experiments of face recognition demonstrate that the combination of original face images and new representations of the original face images is more effective than the only original images. Especially, the simultaneous use of the 2D-PCA method and sparse representation can extremely improve accuracy in image classification. In this paper, the adaptive weighted fusion scheme automatically obtains optimal weights and it has no any parameter. The proposed method is not only simple and easy to achieve, but also obtains high accuracy in face recognition.