Learn More
Within the past decade, major advances have occurred in face recognition. With few exceptions, however, most research has been limited to training and testing on frontal views. Little is known about the extent to which face pose, illumination, expression, occlusion, and individual differences, such as those associated with gender, influence recognition(More)
We aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerative segmentation from superpixels. Our method combines multiple features at all scales of the agglomerative process, works for data with an arbitrary number of dimensions, and(More)
This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for(More)
Parameter indeterminacies are inherent in 3D computer vision. We show in this thesis that how they are treated can have significant impact on the accuracy of the estimated 3D structure. However, there has not been a general and convenient method available for representing and analyzing the indeterminacies and their effects on accuracy. Consequently , up to(More)
Segmentation and recognition have long been treated as two separated processes. We propose a mechanism based on spectral graph partitioning that readily couple the two processes into one. A part-based object recognition system detects parts, supplies their partial segmentations and an evaluation of how well possible labellings on these parts go together(More)
h many computer vision applications it is necessary to compute the direction of heading of a moving camera from the images it produces. Traditionally, this computation has been baaed on the optical flow, that is, on the motion of point features in the field of view. We show that the differential changes in the angles between the projection rays of pairs of(More)
We analyze the feedback loop in Tele-Graffiti, a camera-projector based remote sketching system which we recently developed. We derive the gain through the feedback loop and the final images that will be viewed by the users of the system. We then derive the " optimal gain " as the gain that results in the final viewed images being as close as possible to(More)
We present a new algorithm for automatic inference of human upper body motion in a natural scene. The initial motion cues are first detected from the captured video. A graph model is proposed for human upper body motion, and motion inference is posed as a mapping problem between state nodes in the graph model and the motion cues in images. Belief(More)
The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of the Carnegie Mellon University or the U.S. Government or any of its agency. Abstract A layer is a 2D sub-image inside which pixels share common apparent motion of some 3D scene(More)