The saddle point framework provides a convenient way to formulate many convex variational problems that occur in computer vision. The framework unifies a broad range of data and re...
Jan Lellmann, Dirk Breitenreicher, Christoph Schn&...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
A detailed, comparative study of the numerical stability of the recursive algorithms, widely used to calculate the Zernike moments of an image, is presented in this paper. While m...
George A. Papakostas, Yiannis S. Boutalis, Constan...
In this paper, the development of a three-dimensional (3-D) odometry system for wheeled robots on loose soil in an application of planetary exploration is described. When a wheele...
Spectral clustering is one of the most widely used techniques for extracting the underlying global structure of a data set. Compressed sensing and matrix completion have emerged a...