We present an algorithm that extracts the largest shape within a specificclass, starting from a set of image edgels. The algorithm inherits the Best-First Segmentation approach [jp...
We present a robust camera pose estimation approach for stereo images captured in untextured environments. Unlike most of existing registration algorithms which are point-based an...
Wei Guan, Lu Wang, Jonathan Mooser, Suya You, Ulri...
Since the work by Osher and Sethian on level-sets algorithms for numerical shape evolutions, this technique has been used for a large number of applications in numerous fields. In...
Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their content, and thus remains an important step in many computer vision ...
Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xi...
The emerging MPEG-7 standard embodies a visual descriptor that will be associated with the dominant colors of an image. In this contribution, a threshold adaptation method for reg...