Abstract. In this paper, we propose a novel method for generic object recognition by using higher-order local auto-correlations on probability images. The proposed method is an ext...
The use of higher-order local autocorrelations as features for pattern recognition has been acknowledged since many years, but their applicability was restricted to relatively low...
While tensors occur in many areas of science and engineering, little has been done to visualize tensors with order higher than two. Tensors of higher orders can be used for exampl...
In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the ...
Using local features with nearest neighbor search and direct voting obtains excellent results for various image classification tasks. In this work we decompose the method into its...
Daniel Keysers, Hermann Ney, Roberto Paredes, Tobi...