AI-based OCR system improves quality control and traceability

Cognex Corporation has extended the abilities of its In-Sight 2800 vision system to incorporate OCR. The new ViDi EL Read tool, powered by edge learning technology, easily interprets human-readable characters on reflective, low-contrast and non-flat surfaces.

“The In-Sight 2800 with edge learning redefines ease of use, allowing anyone to deploy AI-based applications regardless of experience level,” said Lavanya Manohar, Cognex vice president of Vision Systems. “ViDi EL Read replaces complicated programming with example-based training, making it simple to set up OCR models to read characters on challenging surfaces and even multiple lines of text simultaneously.”

The easy-to-use OCR solution assists food and beverage producers in readily reading expiration dates, even on curved surfaces, to verify freshness and stop consumer recalls. Medical device and pharmaceutical companies can verify dates and lot codes to provide vaccine efficacy and compliance with medical standards. EV manufacturers can swiftly locate and read the alphanumeric text laser etched on the bottom sides of EV batteries to enhance traceability, and logistics facilities can decipher codes and text on various package types to offer proper routing and stop rework.

OCR applications can be time-consuming to set up, needing hours of programming by highly trained engineers, stopping many companies from automating this type of inspection. Using the tool, models are set up and deployed straight on the device in minutes with as few as ten sample images. The accuracy of the results is measured by a confidence score displayed below each of the trained characters providing real-time visual feedback and reassurance of reliable traceability across the supply chain.

The vision system was first released in April 2022 and was created to solve complex classification applications. Further tools are currently in development and scheduled for release in the coming months.