AI solutions with machine learning (ML) differ greatly in their approach from traditional image processing. In contrast to the manual development of program code, machine learning involves a learning process with suitable image data. However, the selection of this data harbors a high potential for error. In practice, the AI is sometimes provided with images with unimportant content, poor lighting, blurring or even incorrect labels.

The key skills for working with ML methods are therefore not the same as for rule-based image processing - and the provision of hardware alone is not enough. The AI must be tested, validated, retrained and finally integrated into the application in order to guarantee a productive workflow.

Software as a trailblazer

With its IDS NXT platform, IDS shows that this does not necessarily require a system programmer. The idea behind it: With the right, coordinated tools, every user group can fully exploit the potential of the AI vision without having to invest a lot of time and money in building up new core skills. Specialist knowledge for training neural networks and programming your own applications can be packaged in the tools for many simple AI workflows. This means that every user can implement their individual requirements without having to set up their own team of specialists. The software provides each user group with the right tools for their respective tasks and working methods.

The majority of common image processing applications work with relatively simple processes. Capture image, analyze image, make process decisions, initiate action - basic functionalities that differ in just a few details and therefore do not need to be reprogrammed each time. However, the selection of a deep learning (DL) use case, such as "classification" or "object detection", is often already too abstract as an entry point for a project to be able to derive the further action steps required for data acquisition and vision app configuration.

IDS is therefore taking the path of making the AI vision accessible and easy to use for the general public with IDS NXT inference cameras. To this end, the cloud-based training platform for artificial neural networks (ANN) IDS NXT lighthouse is being expanded to include an application assistant that queries tasks such as "count objects" or "check inspection points". The assistant selects the app base with the appropriate use case in the background and suggests further actions to the user. It also provides useful tips, videos and instructions. This type of guided application creation is more reminiscent of a tutorial than classic app development. At the end, a fully customized vision app is available for download, which the user only needs to activate and start on an IDS NXT camera.

"Puzzling" instead of programming

IDS also offers the option of visual programming using a modular system for creating your own complex processes. A decisive advantage of such puzzled apps is their very dynamic use. An application created in IDS NXT lighthouse can simply be further programmed interactively after initial tests in the camera - directly in the camera. Vision apps can even be designed directly there. This makes this visual app editor a suitable tool from the test and trial phase through to operational use.

Inference cameras with AI accelerators show how efficiently AI can already be used. On the way to widespread use, manufacturers in particular are required to support users with user-friendly software and integrated processes. Compared to the tried-and-tested processes that have built up a loyal customer base over the years, AI still has a lot of catching up to do. Standards and certifications are currently being developed to further increase acceptance and explainability.

Ultimately, everyone should familiarize themselves with the new technology so as not to miss the boat. An embedded AI system such as IDS NXT helps with this, as it can be operated quickly and easily by any user group with user-friendly software tools - even without in-depth knowledge of machine learning, image processing or application programming.

Dipl.-Ing. Heiko Seitz, IDS Imaging Development Systems