Orthogonal autoencoder regression for image classification

Least squares regression (LSR) and its extended methods are widely used for image classification. However, these LSR-based methods do not consider the importance of global information and ignore the connection between feature learning and regression representations. To address these problems, we propose a novel method called orthogonal autoencoder regression (OAR) that considers global information by combining the feature learning part with the regression representation part. In addition, to enhance the model’s feature learning ability, we introduce an orthogonal autoencoder model to learn more effective data. To promote the model’s regression representation ability, we also add weight constraints to the model and make the OAR more discriminative. An iterative algorithm with the alternating direction method of multipliers (ADMM) is proposed to solve the model. The experimental results from several databases demonstrate the effectiveness of the OAR.