Synthetic Data and Artificial Intelligence Combine to Improve Machine Vision

May 11, 2022
By creating synthetic data from 3D CAD data, Siemens’ SynthAI helps machine vision systems be more rapidly deployed for applications ranging from quality control to robotic picking and assembly operations.

With its ability to help automate quality control, guide flexible pick-and-place systems, and simplify inventory tracking procedures, machine vision is of growing importance to industrial automation technology. For some time now, artificial Intelligence (AI) has played a significant role in helping manufacturers make use of machine vision and these advances show no sign of slowing down in the near term. One example of this continuing advance of AI and machine vision is Siemens Digital Industries Software's SynthAI service, which uses AI and machine learning to train machine vision systems more effectively.

While the images captured by a machine vision system cannot be analyzed without some type software algorithm, most machine vision software uses fixed-rules determined by a human programmer. In these cases, data is extracted from images in the form of various criteria such as measurement or object type and then compared against pre-established target values to make a decision. This requires many images of an object to be taken.

The application of synthetic data for machine vision training can dramatically speed up the training process. However, using synthetic data for machine vision applications requires expertise in synthetic image generation, which is complex, labor intensive, and costly. To broaden the use of synthetic data beyond the realm of experts, SynthAI allows 3D CAD (computer-aided design) data to be used for machine vision system training instead. By ingesting the CAD data for a given item, SynthAI can generate thousands of randomized synthetic images and annotate them within minutes without specialized expertise.

SynthAI’s capabilities enable it to train a machine learning model from CAD data that can then be used to detect products in real life. Once the training is complete, the model can be downloaded, tested, and deployed in machine vision systems offline. Industrial applications for Siemens SynthAI include quality inspections, flexible robotic assembly, robotic picking and sorting and kitting.

“We were looking for a quick and easy solution that would enable us to detect wire terminals in a robotic electric cabinet assembly station. With SynthAI our control engineers were able to achieve great results within just a few hours,” said Omer Einav, CEO at Polygon Technologies, a supplier of robotics technologies. “The tedious task of annotating a large set of training images to train the model was shortened significantly. The results show great promise for many additional use cases we plan to handle with SynthAI."

Companies in this Article

Sponsored Recommendations

Strategizing for sustainable success in material handling and packaging

Download our visual factory brochure to explore how, together, we can fully optimize your industrial operations for ongoing success in material handling and packaging. As your...

A closer look at modern design considerations for food and beverage

With new and changing safety and hygiene regulations at top of mind, its easy to understand how other crucial aspects of machine design can get pushed aside. Our whitepaper explores...

Fueling the Future of Commercial EV Charging Infrastructure

Miguel Gudino, an Associate Application Engineer at RS, addresses various EV charging challenges and opportunities, ranging from charging station design strategies to the advanced...

Condition Monitoring for Energy and Utilities Assets

Condition monitoring is an essential element of asset management in the energy and utilities industry. The American oil and gas, water and wastewater, and electrical grid sectors...