Subutai Ahmad

A usable real-time 3D hand tracker

This paper presents a computer vision system for tracking human hands. The algorithms used to extract the 3D position, and planar orientation of the hand, and the joint angles of the fingers are described. The combined system is able to track a natural hand at 30 frames per second on a standard workstation with no special image processing hardware other than a frame grabber. The tracker has been used as an interface for navigating around virtual worlds.<<ETX>>

Representing Probabilistic Rules with Networks of GaussianBasis Functions

There is great interest in understanding the intrinsic knowledge neural networks have acquired during training. Most work in this direction is focussed on the multi-layer perceptron architecture. The topic of this paper is networks of Gaussian basis functions which are used extensively as learning systems in neural computation. We show that networks of Gaussian basis functions can be generated from simple probabilistic rules. Also, if appropriate learning rules are used, probabilistic rules can be extracted from trained networks. We present methods for the reduction of network complexity with the goal of obtaining concise and meaningful rules. We show how prior knowledge can be refined or supplemented using data by employing either a Bayesian approach, by a weighted combination of knowledge bases, or by generating artificial training data representing the prior knowledge. We validate our approach using a standard statistical data set.

Analysis-by-synthesis dissolve detection

The paper presents a novel, real-time, minimal-latency technique for dissolve detection which handles the widely varying camera techniques, expertise, and overall video quality seen in amateur, semi-professional, and professional video footage. We achieve 88% recall and 93% precision for dissolve detection. In contrast, on the same data set, at a similar recall rate (87%), DCD (double chromatic difference) has more than 3 times the number of false positives, giving a precision of only 81% for dissolve detection.