Best practice with image targets
For good results using image recognition and tracking we suggest ...
For best results follow these tips:
between 500 to 1000 pixels in each dimension
An aspect ration roughly square
Rich contrast
Evenly distributed textured areas
Many corner like structures
Smaller dimensions than 500 pixels
Larger than 1000 pixels as they do not provide more accurate results
Extreme aspect ratios
Large amounts of text
Many repetitive patterns
Large single-colored areas
Color contrast only e.g. green to red edge)
PREFERRED IMAGES HAVE:
UNSUITABLE IMAGES HAVE:
Optimal Image Dimensions
Mock-ups only
Optimal images are sized between 500 and 1000 pixels in each dimension
Small images do not contain enough graphical information to extract so called feature points. The uniqueness, amount and distribution of features points are the key indicators for good detection and tracking quality
Larger images do not improve the tracking quality
Squarish aspect ratio
Mock-ups only
Ideal images have an aspect ration around 1:1
Other aspect ratios like 3:4, 2:3 up to 16:9 will perform good as well
Panorama images or other images with extreme aspect ratios won’t deliver the optimal tracking performance
Tip: Try to crop the most prominent squarish part of your image and use only this as target image.
Low contrast images
Mock-ups only
Images with high local contrast and large amount of rich textured areas is best suited for reliable detection and tracking
Color contrast only (i.e. green to red edge) appears as high contrast to the human eye but is not discriminative to computer vision algorithms as they are operating on grayscale images
Tip: For low contrast images, try to increase the contrast of your target image with an image editing tool like Gimp or PhotoShop to improve detection and tracking quality
Distribution of textured areas
Mock-ups only
Images with evenly distributed textured areas are good candidates for reliable detection and tracking
This might be the hardest part to be in control of and often can’t be changed.
Tip: Try to crop the most prominent part of your image and use only this as target image.
Images with whitespace
Single-colored areas or smooth color transitions often found in backgrounds do not exhibit graphical information suitable for detection and tracking.
Tip: Try to crop the most prominent part of your image and use only this as target image.
Vector-based graphics
Mock-ups only
Logos and vector-based graphics usually consist of very few areas with high local contrast and textured structures and are therefore hard to detect and track.
Tip: Try to add additional elements to the graphic like your logotype or any other specific elements, which can go along with your graphic.
Images with a lot of text
Mock-ups only
Images consisting primarily of large areas of text are hard to detect and track.
Tip: Try to have at least some graphical material and images next to your text for your target image.
Repetitive patterns
Mock-ups only
Repetitive patterns exhibit the same graphical information information at each feature point and therefore cannot be localized reliably (first image)
Images with slightly irregular structures can convey a similar information to the target audience while providing enough unique feature points to be detected (second image)
Tip: Try a different selection of your image including non pattern parts or use images with irregular patterns
By Andrew Craigie
About the Star rating
The star rating you see when you upload your image is only a first estimation of how well we expect your target to work.
Even images with a low initial rating (like 0 or 1 stars) may work fairly well.
An image does not need 3 stars to work well. A 2‑star rating is already very good and will deliver good results in the most conditions.
Tip: Try out your image even if it gets an initial 0 star rating. Images with a 2-star do not need any more optimization for the most use-cases.
Devices with optimal performance
Devices with optimal performance
General characteristics of well suited devices• Devices with a dual core CPU and support for NEON instructions• Devices that are under two years old
Android devices like:• Samsung S2, S3, S4• Sony Xperia Z• Google Nexus 4, Galaxy Nexus
iOS devices like:• iPhone 4S, iPhone 5• iPod Touch 5th generation• iPad 2 – 4, iPad mini, iPad Air