Wilman W. W. Zou

Learn More
This paper addresses the very low resolution (VLR) problem in face recognition in which the resolution of the face image to be recognized is lower than 16 × 16. With the increasing demand of surveillance camera-based applications, the VLR problem happens in many face application systems. Existing face recognition algorithms are not able to give(More)
This paper proposes a new nonlinear face super resolution algorithm to address an important issue in face recognition from surveillance video namely, recognition of low resolution face image with nonlinear variations. The proposed method learns the nonlinear relationship between low resolution face image and high resolution face image in (nonlinear) kernel(More)
Supervised manifold learning has been successfully applied to action recognition, in which class label information could improve recognition performance. However, the learned manifold may not be able to well preserve both the local structure and global constraint of temporal labels in action sequences. To overcome this problem, this paper proposes a new(More)
In many practical video surveillance applications, the faces acquired by outdoor cameras are of low resolution and are affected by uncontrolled illumination. Although significant efforts have been made to facilitate face tracking or illumination normalization in unconstrained videos, the approaches developed may not be effective in video surveillance(More)
A Brillouin fiber laser using a highly nonlinear birefringent photonic crystal fiber is reported. The core of the fiber was elliptical in shape. A single-longitudinal-mode high power fiber laser was used as a Brillouin pump and the laser produced multiwavelength output with a 0.04 nm separation. Adjusting the polarization controller plates made it possible(More)
In practical face tracking applications, the face region is often small and affected by illumination variations. We address this problem by using a new feature, namely the Gradient-Logarithmic Field (GLF) feature, in the particle filter framework. The GLF feature is robust under illumination variations and the GLF-based tracker does not assume any model for(More)
  • 1