EasyAR: How to create a reliably trackable image target?

I'm using EasyAR Sense for Unity to develop an app that tracks a target image. I'm using https://www.easyar.com/targetcode.html to test my target images, but I have not yet understood the markers requirements. Are the colors of image important? Or is it based on the recognition of outlines and edges?

Also, are there any suggested guidelines and how do they apply to random images? (just to clarify, i'm not interested in using markers but digitally drawn pictures).

EDIT: We found out that the ways in which Vuforia and EasyAR recognize theyirtargets are pretty far apart from each other. An image that would rate fairly low on Vuforia will score high on EasyAR's site and vice-versa.

As far as we know now, yes, Vuforia bases its recognition methods on high contrasts and sharp edges. That said, Vuforia as a solution is not feasible for our purposes, as it doesn't support front facing camera. We had to look for alternate solutions and stumbled across EasyAR which seems powerful, but with a really slim documentation on the programming side, and an inexistent design guideline documentation.

As we understand chaotic patterns will be recognized the best from EasyAR's engine but it doesn't state how much chaos defines "a rich texture". But we are in dire need of simplicity in the images we're using in the application since it's targeted towards kids with understanding disorders, and a messy approach to the images may be counterproductive.

Upvotes: 2