Best Practices for Designing and Developing Image-Based Targets

When it comes to image-based targets, there are a range of factors that define how well it tracks and its target star rating when uploaded to the Vuforia Target Manager. This guide will provide you with insight into what makes a good Image Target.

Image-based targets come in various forms: simple, flat Image Targets, curled targets in form of cylindrical shapes, or Multi-Targets in the composition of a box. They all share similar requirements for having rich detail and a good star rating. This article focuses on Image Targets, but the same factors apply to Vuforia’s other image-based targets. Besides designing a good Image Target, it is also advisable to consider the Physical Properties of Image Targets.

Attributes of an Ideal Image Target

Image Targets that possess the following attributes will enable the best detection and tracking performance from the Vuforia Engine.



Rich in detail Street scene, group of people, collages and mixtures of items, and sport scenes are good examples.
Good Contrast Images with bright and dark regions and well-lit areas work well.
No repetitive patterns Employ unique features and distinct graphics covering as much of the target as possible to avoid symmetry, repeated patterns, and feature-less areas.
Format Must be 8- or 24-bit PNG and JPG formats; less than 2 MB in size; JPGs must be RGB or greyscale (no CMYK).

Example Image

Figure A – Image Target with coordinate axes for explanation.

This image is fed into the online Target Manager to create the target database.

Figure B – Image showing the natural features that the Vuforia Engine uses to detect the Image Target.

Target Star Rating

Image Targets are detected based on natural features that are extracted from the target image and then compared at run time with features in the live camera image. The star rating of a target ranges between 1 and 5 stars. Although, targets with low rating (1 or 2 stars) can usually detect and track, aim for targets with 4 or 5 stars for best results.

To create a target that is accurately detected, you should use images according to the above attributes for an ideal Image Target.

Natural Features and Image Ratings

An augmentable rating defines how well an image can be detected and tracked using the Vuforia Engine. This rating is displayed in the Target Manager and is returned for each uploaded target via the web API, when using Cloud Reco Databases.

The augmentable rating can range from 0 to 5 for any given image. The higher the augmentable rating of an image target, the stronger the detection and tracking ability it contains. A rating of zero indicates that a target is not tracked at all by the AR system, whereas a star rating of 5 indicates that an image is easily tracked by the AR system.

Rating - Features

A feature is a sharp, spiked, chiseled detail in the image, such as the ones present in textured objects. The image analyzer represents features as small yellow crosses. Increase the number of these details in your image and verify that the details create a non-repeating pattern.

A square contains four features for each one of its corners.
A circle contains no features as it contains no sharp or chiseled detail.
This object contains only two features for each sharp corner.
Note: According to the definition of a feature, soft corners and organic edges are not marked as features.

Comparison of two images

Inspect the two images and notice the lack of feature points in the first image. It is always advisable to design and find images that show a significant amount of points. As described later, an even distribution of feature points also improves tracking and the robustness of your augmentations: your augmented content is steadier when they are placed on top of a feature rich area of your Image Target.

Rating – Contrast

The artwork below shows a more practical example of how to improve the local contrast of the target. We use an image with two layers. In the foreground are a few multi-colored leaves. The background is a textured surface. The layers exist only in our graphic editor; when uploading to the Target Manager, we always use a flattened image, e.g., PNG format. The uploaded image is 512x512 pixels in size, a little bigger than the recommended minimum of 320 pixels.

At first sight, the original image might have enough detail to function as a target. Unfortunately, uploading it to the Target Manager yields a very low rating of only one star. This results in poor tracking performance. Consecutive adjustments on the image improves the target quality to a five-star target, yielding superior detection and tracking performance.

Applied Improvements:

  • Background layer changed to a lighter color resulting in more features points.
  • Foreground features adjusted with higher contrast and lower brightness.
  • Local contrast enhancement applied to image.

Further Improvements

  • Reduce background to white.
  • Strengthen contrast along edges.

The result is a five-star rating of the image that will track well and consistently. The contrast and features will be easily picked up and the placement of augmentations can be positioned at any position as the feature distribution is consistent. For guides and other improvements to the image, please refer to Image Targets Optimization Techniques.

Rating - Feature distribution

The more balanced the distribution of the features in the image, the better the image can be detected and tracked. Verify that the yellow crosses are well-distributed across the entire image. Poor feature distribution as in this image affect the rating and performance of the target image. Cropping the image to remove any areas without features may improve the overall rating of the image.

Additionally, this image also suffers from poor contrast between trackable features and the background. The objects in this image lack the sharper edges and clearly defined shapes for a better rating and performance.

Rating – Organic Shapes

Typically, organic shapes with soft or round details containing blurred or highly compressed aspects do not provide enough detail to be detected and tracked properly or not at all. They suffer from a very low feature count.
In this image there are no features because it lacks visual elements with sharp edges and high contrast. The Vuforia Engine will fail to detect and track images that display these or similar characteristics.

Rating - Repetitive Patterns

Although some images contain enough features and good contrast, repetitive patterns hinder detection performance. For best results, choose an image without repeated motifs (even if rotated and scaled) or strong rotational symmetry. A checkerboard is an example of a repeated pattern that cannot be detected, since the 2x2 pairs of black and white squares look exactly the same and cannot be distinguished by the detector.

Rating - Non-Rectangular Image Targets

The target image used does not require to always be rectangular. You can use non-rectangular 2D shapes as targets by placing the image of the shape on a white background with a visible outline. This will ensure that only the features of the shape are used for the Image Target.

The Feature-Exclusion Buffer

A feature’s exclusion buffer surrounds the inset of an uploaded image. This buffer area is about 8% wide and it does not pick up any features, even if features do exist within that zone. The first row of the following table shows where the shaded area in red does not contain any features, even though visible features are present in this zone.

  Uploaded Image Analyzed Image (Red Marking)
Original Image Target
Image Target with border

You can avoid this feature-exclusion buffer situation by adding a white 8% buffer around the image for the Target Manager target generation, as shown in the lower row of the table above. But consider that those features will be helpful only when it can be guaranteed that during the run time execution the target will lie on a surface with a unique color that does not itself have features.

Can this page be better?
Share your feedback via our issue tracker