Wikitude SDK 8.5: New Image Recognition Features And Improvements

Eva Triantafillopoulou

Image Recognition just got better! Wikitude developers are now able to recognize even more types of targets and can enjoy new SDK features and performance updates.

As a result of our latest product improvement cycle, we are proud to present Wikitude SDK 8.5. The update offers even more stability to the platform and introduces two brand new Image Recognition features:

  • Transparent Areas in Image Targets
  • Image Targets at Runtime

New Image Recognition Features and Improvements

Wikitude Image Recognition is one of the best performing AR technologies on the market. But don’t take our word for it – we confidently invite any interested party to download a free trial and let the product speak for itself.

And, even though Wikitude has been offering Image Recognition since 2012, we are still eagerly committed to pushing the boundaries of what’s possible with this AR technology. Today we are excited to introduce two new Image Recognition features.

Transparent Areas in Image Targets

The new Transparent Area feature has been included to support those special types of image targets that do not fit the typical rectilinear image shape.

Examples of such images containing transparent areas beyond the main outlines include tattoos, stickers, logos, images with cutouts and basically any image file containing parts with alpha channel transparency.

Details at a glance:

  • Images with transparent areas can now be used as Target Images
  • Transparent areas will be ignored during the recognition and tracking process
  • Works with Image Targets at Runtime, not with WTC files
SDK 8.4 (without transparency support – WTC) X SDK 8.5 (with transparency support)

Image Targets at Runtime

Traditionally, Image Recognition requires developers to create an Image Target collection (WTC file), previous to the AR experience, to be used to detect and track images. As efficient and well-performing as this process may be – and it will continue existing as is, developers now have an additional option to create Image Targets.

With the new Image Targets at Runtime functionality, developers can create Image Targets on the fly, no need for preprocessing.

Details at a glance:

  • Use regular images (png, jpg,…) directly with SDK as target images
  • Multiple images can be bundled into a zip file
  • No need for WTC file creation
  • Working with WTC files remains as is

Being able to define Image Targets at runtime means users have the ability to easily create AR experiences on the spot. Ideal for quick and convenient testing during the development phase.

Also practical for spontaneous use cases on the go: demos during networking, dynamic art projects, in a classroom environment, adding AR to game cards, and more.

As mentioned above, Runtime Targets give Wikitude developers yet another target creation option. However, the traditional WTC file target collection methods continue to offer advanced functionalities, such as target image performance ratings and manual height value input fields. Ideal for AR experiences that require fine tuning and precise input for even more accurate distance to target calculation and proper wearable device calibration.

Image Recognition Performance Improvements

SDK 8.5 is a big release for Image Recognition AR technology. Alongside the new features presented above, the update is bringing significant performance advancements. Not only are image targets being recognized faster, but they are also being recognized from even further away. Check the details below:

Recognition distance

Image Targets can now be recognized from more than three meters away. To be more precise, we tested an A4 / US-letter sized image target and SDK 8.5 was able to recognize it from 312cm away. That is a whopping +40% increase in distance from previous SDK versions.

Regardless of the target size, our performance tests show that, with SDK 8.5,  image targets can be recognized even when they occupy a mere 1% of the device screen area. In other words, this update is ideal for use cases in which users do not have the target image within hands reach.

Duplicate Targets

With a growing demand for multiple and duplicate target Image Recognition, on this release, our team focused on improving duplicate target handling. Wikitude developers will notice faster recognition when it comes to duplicate targets.

Recognition Speed and Tracking Stability

As AR technology provider pioneers, Wikitude takes pride in the quality and performance of its Image Recognition technology. And thanks to the natural advancements in processing capacity of devices, camera optics and related technology in general, we are able to expand the performance and capability of our own AR technology along the way. With this 8.5 release, expect substantial improvements in image recognition speed and tracking stability.

Update to the iOS sample project – now based on Swift 4.2

Apple has been progressing the Swift programming language quite fast since its inception in 2014. Nearly every year a new major version was released by Apple. As part of the Wikitude SDK, we are shipping sample applications, that show the integration of the Wikitude SDK and how to use the APIs to create AR experiences. The Swift-based sample project was already a little bit rusty and still based on Swift 3 – in SDK 8.5 the project is now based on Swift 4.2 and is compatible with the latest Xcode version.

AR SDK enhancements, fixes, and stability improvements

In parallel to the new components and innovative solutions that are frequently being added to the Wikitude AR feature set, our augmented reality SDK is also constantly being submitted to rigorous quality tests to ensure that Wikitude developers have access to the finest and most comprehensive AR tools on the market.

Wikitude SDK 8.5 includes a series of fixes and stability improvements. Please review the release notes for your platform for an in-depth report.

Download Wikitude SDK 8.5

Active Wikitude SDK subscribers are entitled to any and all SDK version updates that are released throughout their term. All other parties are invited, however, to download a free Wikitude SDK 8.5 trial version for testing purposes.

Access our download page to explore all options or click on the direct links below to begin downloading now. Once the download is complete you will be automatically redirected to the signup/login page.

Wikitude AR SDK for Android
Download Wikitude SDK 8.5 for Android JavaScript API
Download Wikitude SDK 8.5 for Android Native API

Wikitude AR SDK for iOS
Download Wikitude SDK 8.5 for iOS JavaScript API
Download Wikitude SDK 8.5 for iOS Native API

Wikitude AR SDK for Windows
Download Wikitude SDK 8.5 for UWP Native API

Wikitude AR SDK for Unity
Download Wikitude SDK 8.5 for Unity

Wikitude AR SDK for Cordova
Download Wikitude SDK 8.5 for Cordova

Wikitude AR SDK for Xamarin
Download Wikitude SDK 8.5 for Xamarin

Interested in keeping your app running smoothly and always compatible with operating system device updates. Send us an email to learn how you can get 1+ year of SDK upgrades through our increasingly popular subscription program.

New to Wikitude? Access our store to choose your package or contact our team to discuss your specific AR requirements in detail.

Attending AWE USA 2019 in Santa Clara, CA? Make sure to visit Booth 419 to check cool SDK 8.5 demos and meet the Wikitude team. CTO Phil Nagele will also be talking about scanning and using 3D objects in AR experiences on mobile and smart glasses at the developer track on May 30. More details and Promo Discount code here. Don’t miss out!

Previous Article
Join Wikitude at AWE USA 2019
Next Article
Join Wikitude at AWE USA 2019