Abstract
The fact that image data samples lie on a manifold hasbeen successfully exploited in many learning and inferenceproblems. In this paper we leverage the specific structureof data in order to improve recognition accuracies in gen-eral recognition tasks. In particular we propose a novelframework that allows to embed manifold priors into sparserepresentation-based classification (SRC) approaches. Wealso show that manifold constraints can be transferred from the data to the optimized variables if these are linearly cor-related. Using this new insight, we define an efficient al-ternating direction method of multipliers (ADMM) that can consistently integrate the manifold constraints during the optimization process. This is based on the property that we can recast the problem as the projection over the manifold via a linear embedding method based on the Geodesicdistance. The proposed approach is successfully applied on face, digit, action and objects recognition showing a consistently increase on performance when compared to the state of the art.