Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
The ability to extract and follow time-varying flow features in volume data generated from large-scale numerical simulations enables scientists to effectively see and validate mod...
Content-based retrieval and recognition of graphic images requires good models for symbol representation, able to identify those features providing the most relevant information a...
Boosting is a remarkably simple and flexible classification algorithm with widespread applications in computer vision. However, the application of boosting to nonEuclidean, infini...
This paper gives an overview over several techniques for detection of features, and in particular sharp features, on point-sampled geometry. In addition, a new technique using the...