AI methods have been successfully involved in image processing with great success. Neural networks recognize everyday objects with greater accuracy than humans. Fraunhofer Institute for Production Systems and Design Technology IPK has adapted the algorithms for industrial applications.
What is all about?
App enables individual components with no barcode to be unambiguously identified within seconds. Various industries and enterprises are going to get the maximum profit from this technology. For instance, logistics companies, which can use them to speed up their incoming goods processes.
Companies are increasingly producing goods at different locations, working with multiple supply companies. But how can they be sure that all the components they receive are labeled properly with barcodes or type plates? There is no guarantee that objects are properly categorized in the receiving area. In the case of discrepancies, recategorization is much needed. It means that employees have to manually search the catalog for similar parts to unambiguously identify them for further logistics processing—a painstaking and time-consuming task.
Here Comes Solution
Automated, digitalized recognition would be helpful to speed up the process. Researchers at Fraunhofer IPK in Berlin are now working on this task—applying machine learning methods. They use what are known as convolutional neural networks (CNNs) to recognize manufactured components, such as screws, clamps, nozzles, pipes, tubes and cables, as well as microcontrollers and other electronics.
The designers claim that the app recognizes a wide array of different components. "We use specially developed algorithms to limit the search radius to five or ten objects, so employees no longer have to search through the entire range typically found in a large warehouse." - says Mr. Jan Lehr, the head of the research team.
Operation principle
The project on developing a detection system is called Logic.Cube. The objects to be recognized are placed in the cube-shaped device with an integrated scale and are photographed by up to nine cameras. An image processing algorithm measures the objects' height, width and length in order to calculate what size box or shelf space is needed. The resulting image set goes to a database, together with the material number. This image data is used to train the AI algorithm to enable it to recognize a wide array of different components.
High recognition rates with few images
Not every company will consider purchasing the Logic.Cube. So the Fraunhofer IPK research team ported the detection system's functionality to a browser-based, operating system-independent app that works on smartphones, tablets, laptops and desktop computers. To do this, they had to expand the training dataset to include smartphone data and retrain the algorithm. Within seconds, the app shows the user five or fewer potential matches, independent of lighting, background and scenery. This saves workers an incredible amount of time. The programmers have managed to achieve high recognition rates with a minimum of images. The researchers reached recognition rates of 98 percent in Logic.Cube and reduced the search radius from 4500 images to five. They aim to get the same success rate with the app.
Comments