Legibility Estimation for Projected AR Contents

Projected Augmented Reality (projected AR) is technology that directly overlays digital contents onto physical objects by using projectors. When texts are projected as the AR contents, their legibility is one of the most vital matters. Accordingly, several projector-camera systems have been proposed for improving the legibility of projected contents, where projection conditions are adjusted according to the legibility estimated from captured images of projected contents. This paper proposes a novel method for estimating the legibility of projected contents, which takes into account the effect of a patterned projection surface by using edge information in the captured images of projected contents.