We present a new method for detecting interest points
using histogram information. Unlike existing interest point
detectors, which measure pixel-wise differences in image
intens...
Wei-Ting Lee (National Tsing Hua University), Hwan...
This paper describes a probabilistic multiple-hypothesis framework for tracking highly articulated objects. In this framework, the probability density of the tracker state is repr...
We present a technique to reduce image blur caused by out-of-focus regions in projected imagery. Unlike traditional restoration algorithms that operate on a blurred image to recov...
Outdoor face recognition is among the most challenging problems for face recognition. In this paper, we develop a discriminant mutual subspace learning algorithm for indoor and ou...
We present a single-image highlight removal method that incorporates illumination-based constraints into image inpainting. Unlike occluded image regions filled by traditional inpa...
Ping Tan, Stephen Lin, Long Quan, Heung-Yeung Shum