We introduce and analyze a new algorithm for linear classification which combines Rosenblatt's perceptron algorithm with Helmbold and Warmuth's leave-one-out method. Like...
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAM)-based approaches have achieved some success, t...
As increasing amounts of sensitive personal information is aggregated into data repositories, it has become important to develop mechanisms for processing the data without revealin...
In this paper, we propose a new method for face detection from cluttered images. We use a polynomial neural network (PNN) for separation of face and non-face patterns while the co...
A single face classifier has difficulty in detecting multiview faces under real and complex scenes due to various poses, cluttering environment and small size of faces. In this pa...