This paper describes an efficient feature selection method that quickly selects a small subset out of a given huge feature set; for building robust object detection systems. In th...
Standard practices in background modeling learn a separate model for every pixel in the image. However, in dynamic scenes the connection between an observation and the place where...
This paper presents separation of specular and diffuse reflection components from an image pair. The proposed approach is based on the dichromatic reflectance model and Markov ran...
Sang Hwa Lee, Hyung il Koo, Nam Ik Cho, Jong-Il Pa...
A powerful class of attacks in multimedia fingerprinting is known as collusion attacks, where a clique of colluders, each having a copy of the same multimedia content with differe...
We present an approach to estimate the poses of human heads in natural scenes. The essential features for estimating the head pose are the positions of the prominent facial featur...