We propose a scheme to introduce directionality in the Random Walker algorithm for image segmentation. In particular, we extend the optimization framework of this algorithm to com...
We propose a multi-resolution framework inspired by human visual search for general object detection. Different resolutions are represented using a coarse-to-fine feature hierarch...
Wei Zhang 0002, Gregory J. Zelinsky, Dimitris Sama...
Abstract. Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the ...
In this paper we discuss a general framework for feature selection based on nonparametric statistics. The three stage approach we propose is based on the assumption that the avail...
A novel low-computation discriminative feature space is introduced for facial expression recognition capable of robust performance over a rang of image resolutions. Our approach i...