To reduce the classification errors of online handwritten Japanese character recognition, we propose a method for confusing characters discrimination with little additional costs....
Writer adaptive handwriting recognition, which has potential of increasing accuracies for a particular user, is the process of converting a writer-independent recognition system t...
Abstract. We propose a novel framework, aspect space, to balance deformability and discriminability, which are often two competing factors in shape and image representations. In th...
Kernel methods provide an efficient mechanism to derive nonlinear algorithms. In classification problems as well as in feature extraction, kernel-based approaches map the original...
Estimation of three-dimensional articulated human pose and motion from images is a central problem in computer vision. Much of the previous work has been limited by the use of cru...
Leonid Sigal, Alexandru O. Balan, Michael J. Black