What makes a good image target?

What makes a good image target and how will we know that it will track well? We can identify characteristics of the physical target and the image on it.

The target itself should have a matt finish to avoid reflections and specular highlights that might confuse the recognition software when it's processing the video feed at runtime.

It also should be rigid so it won't be distorted or morphed when the camera is viewing it. Thus, a card or paper board won't be able to bend or crease as easily as a regular piece of paper. The tracking will be more consistent.

The image should have a border so it can be readily distinguished from the background. The recommendation is this border should be roughly 8% of the image ...

Get Augmented Reality for Developers now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.