Based on scaling laws describing the statistical structure
of turbulent motion across scales, we propose a multiscale
and non-parametric regularizer for optic-flow estimation.
R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
Histograms of orientations and the statistics derived from them have proven to be effective image representations for various recognition tasks. In this work we attempt to improve...
In this paper we propose a set of algorithms that combine the anisotropic smoothing using the heat kernel with the outlier rejection capability of robust statistics. The proposed ...
Abstract. This paper presents a machine-learning approach to the interactive classification of suspected liver metastases in fMRI images. The method uses fMRI-based statistical mod...
Color features are among the most important features used in image database retrieval, especially in cases where no additional semantic information is available. Due to its compac...