The solutions to many vision problems involve integrating measurements from multiple sources. Most existing methods rely on a hidden assumption, i.e., these measurements are consi...
In this paper, we show how to reconstruct both 3D shape and 2D texture of a class of surfaces from a single perspective image. We consider the so-called the generalized cylindrica...
Relevance feedback approaches based on support vector machine (SVM) learning have been applied to significantly improve retrieval performance in content-based image retrieval (CBI...
In this paper, we describe a new method for camera-based fiducial tracking. Our new method is based on the combination of topological region adjacency and angle information, where...
Non-rigid structure from motion (NR-SFM) is a difficult, underconstrained problem in computer vision. This paper proposes a new algorithm that revises the standard matrix factori...