This paper is aimed at evaluating the semantic information content of multiscale, low-level image segmentation. As a method of doing this, we use selected features of segmentation...
When dealing with pattern recognition problems one encounters different types of a-priori knowledge. It is important to incorporate such knowledge into the classification method ...
— Detecting the boundaries of objects is a key step in separating foreground objects from the background, which is useful for robotics and computer vision applications, such as o...
Kiho Kwak, Daniel F. Huber, Jeongsook Chae, Takeo ...
We present a novel human action recognition system based on segmented skeletal features which are separated into several human body parts such as face, torso and limbs. Our propos...
—The concept of green computing has attracted much attention recently in cluster computing. However, previous local approaches focused on saving the energy cost of the components...
Liting Hu, Hai Jin, Xiaofei Liao, Xianjie Xiong, H...