Computer vision and transparency

By Timothy Bahls

I take two approaches towards transparency: a practical approach and a mathematical approach.

Abstract:

Human eyes are very precise when gauging relative distances if the two distances are aligned and close. However, this ability decreases as the distances are farther apart or misaligned.

Thus we can tell that human eyes are better locally than globally. This suggests that more rigorous local-based methods can make up for less rigorous global methods, and that approaches that devalue global distance information are promising.

The first paper can be downloaded here.

Abstract:

A little bit of physics and math with a smattering of computer science are laid out to begin an approach to handling transparency.

The second paper can be downloaded here.