: Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this arti...
In this paper we present a technique for the tracking of textured almost planar object. The target is modeled as a noisy planar cloud of points. The tracking is led with an approp...
A new criterion based on Gaussian fields is introduced and applied to the task of automatic rigid registration of point-sets. The method defines a simple energy function, which is...
Andreas Koschan, Besma R. Abidi, Faysal Boughorbel...
After a classifier is trained using a machine learning algorithm and put to use in a real world system, it often faces noise which did not appear in the training data. Particularl...
This paper presents a method for recovering 3D facial shape from single image via learning the relationship between the 2D intensity images and the 3D facial shapes. With a couple...
Annan Li, Shiguang Shan, Xilin Chen, Xiujuan Chai,...