What is a target image?
The target image is the digital reference of your real-world anchor which is needed in order to align your AR content with it. Therefore the image should contain enough information to ensure the system is able to provide a good tracking performance. For the best tracking quality, try to stick to the rules below.
Finding good targets.
The genARate platform uses 2D image tracking technology to be able to recognize the target images you have defined as part of your AR scenarios inside the live camera feed of your phone. Since these images are the backbone of each augmented reality scenario and heavily responsible for the quality of the end-user experience you should make sure to select the right target images and settings and test them well before use.
The technology is working based on contrasts – so please make sure to follow this simple rule: "The more rich contrasts the image provides, the better the result of the image recognition will be." But please note that there are exceptions.
Find additional Information about good targets, star rating and target heatmap here.
How to recognize working and non-working Targets
Please keep in mind our rule:
"The more rich contrasts the image provides, the better the result of the image recognition will be!"
Therefore please try to follow the below guidelines and examples:
Even though text provides many contrasts for the human eye, it has a quite negative effect on image recognition since the text normally is too small and too fragile for the used image recognition technology
This might change according to the size of the text, so big headlines might work well
Try to avoid especially text blocks, always try to optimize your target focusing on images, headlines or more prominent graphical elements
Avoid “empty” space.
Avoid areas in your target image which are blank white or in any other monochrome color
Crop the image before the upload or adjust the tracking area during the setup of your WonderPage to exclude these areas if possible
Make sure the contrast points of your image are spread homogenously over the entire image and avoid areas without any contrasts.
Avoid repetitive or “rotation synchronous” patterns.
Images like a chessboard or dartboard might provide a rich set of contrast but since the pattern is repetitive or “rotation synchronous” the algorithm behind the image recognition cannot recognize in which orientation the target is shown to the camera (upwards/downwards, etc.)
as long as the repetitive pattern offers clear information for all four orientations, it should work well (like the sample below with a green frame)
Maybe interesting too: