How imaging and Artificial Intelligence automate complex sorting

The sorting of diverse objects is key task in many production plants and logistic centers. Traditional manual sorting processes consume large amounts of resources and involve significant costs. Using imaging processing technology and machine learning algorithms, it is possible to fully automate complex sorting on the conveyor. The FRAMOS Volume Light Grid (VLG) provides an easy method to integrate Machine Learning processes to new or existing plants.

One of the major challenges facing industrial production and logistics is sorting packages to ensure that they are subsequently processed correctly. Machine sorting is almost impossible because of the wide variety of packaging types with different materials, shapes and sizes and the fact that the parcels are stacked or heaped on the conveyor belt. Large volumes of goods still need to be sorted manually. This leads to considerable costs and slow sorting procedures with high error rates.

Imaging data form the basis for Machine Learning, enabling a fast acquisition and automation of industrial sorting. Cognitive learning processes based on large volumes of data allow machines to learn for themselves. They can tell for example, whether a package is damaged, how it must be classified and sorted or whether it is properly sealed. This type of learned artificial intelligence enables production and logistics processes to be entirely managed by automation.

Fully automated sorting with machine learning

Machine Learning enables self-learning algorithms to control processes. First, a large amount of data is supplied, for example, thousands of images of packages stacked on a conveyor. Pre-classified by a human, the algorithm is told “This is a parcel,” and is then able to sort the packages into categories based on their individual features. The multi-stage classification process uses a neural network, separating the data during several phases to classify it. Intelligently, the machine learns the parameters that identify an object as a parcel. This enables the algorithm to classify individual objects independently in the future.

The image processing specialist FRAMOS has developed a plug-and-play volume measuring system to be integrated at conveyors. The Volume Light Grid (VLG) enables 3D recording of the dimensions and volumes of objects in real-time, providing seamless integration and automated use of this information in every production and logistics capacity. For example, the verified receipt including precise documentation, optimized utilization of storage space, automated processing and picking, and continual quality control. Enriched with Machine Learning algorithms, the VLG is an intelligent solution where conventional imaging has reached its limits, such as sorting a variety of package types. 3D scanners are not an adequate means of identifying the shape of objects and operate only at low speeds. By contrast, systems driven by Machine Learning can accurately identify the objects and their shape. Robots can carry out the sorting process at high speed, without manual intervention.

In addition to the 3D data, industrial cameras can be used. The intelligent algorithm sees the picture, processes earlier-learned patterns and then automatically controls the sorting procedure and issue commands to downstream phases of the process. At the same time, the algorithm is fine-tuning its criteria from each new picture. Image processing using artificial intelligence can create a fully integrated and automated Smart Factory solution using Machine Learning, which is ideal for companies that have large volumes of goods and complex sorting processes.

Machine learning as a strategic competitive advantage

The recorded data can fully analyze all logistics cycles. In automated processes, real-time decisions can be made under constantly changing criteria while being in operation. Production and logistics systems are qualified by Machine Vision to make valid decisions independently. This enables fault-free logistics systems and advance error prevention. Dashboards can be created based on this complete data set that can answer several analytical questions, with connections and insights gained that were not possible in the past. Image processing is no longer simply an inspection procedure, it can now improve production processes. The data processed by intelligent algorithms allow more reliable forecasts and strategic planning. Machines and quotas can be used highly efficiently when sensor systems and databases are networked. This forms the ideal foundation for simplifying workflows, saving resources and having lower handling costs. The objects both pass through and are shipped quicker. This also leads to fewer errors and increased process quality.

Dr. Simon Che’Rose, Head of Engineering at FRAMOS: “The VLG enables fast and straightforward automation to minimize throughput times and lower package and logistics costs. Our many years of expertise in image processing, Artificial Intelligence and Machine Learning guarantee the high quality of the software. The VLG enables process automations such as sorting and orientation tasks and quality assurance. By generating immense value-add and cost advantages in the supply chain, we are making it ready for the future.”

Dr. Christopher Scheubel, Business Development
FRAMOS Electronics Ltd., Suite 2.11 Building 3, Watchmoor Business Park, Riverside Way, Camberley, Surrey GU15 3YL,
info@framos.com, +44 1276 4041 – 40