By simplifying character reading applications, Edge Learning technology improves quality control and traceability.
Cognex Corporation announces that its In-Sight 2800 vision system now includes an optical character recognition (OCR) function. Powered by Edge Learning technology, the new ViDi El Read tool easily deciphers human-readable characters on reflective, non-planar and low-contrast surfaces.
" With Edge Learning technology, the In-Sight 2800 system redefines ease-of-use, enabling any user to deploy AI-based applications, regardless of experience. " said Lavanya Manohar, Cognex Vice President of Vision Systems. " For its part, the ViDi El Read tool replaces complex programming tasks with example-based training, simplifying the configuration of optical recognition models to read characters on difficult surfaces, and even several lines of text simultaneously."
Thanks to its ease of use, OCR software enables food and beverage producers, for example, to easily read expiration dates, even on curved surfaces, in order to verify the freshness of foodstuffs and avoid product recalls by consumers. Pharmaceutical laboratories and medical device manufacturers can check dates and batch codes to ensure that vaccines are effective and comply with current medical standards.
This solution also enables electric vehicle manufacturers to quickly locate and read the laser-engraved alphanumeric text on the underside of the battery fitted to their vehicles, to improve traceability. Finally, logistics centers can decipher codes and texts on different types of packaging, thus ensuring that products are correctly routed and avoiding batch reworking.
Implementing an OCR application is a tedious operation which can require several hours of programming by highly skilled engineers, preventing many companies from automating this type of inspection. With the ViDi El Read tool, templates are directly configured and deployed on the device in just a few minutes, using just 10 sample images. The accuracy of the results is measured by a confidence score displayed under each formed character, offering real-time visual feedback and the guarantee of reliable traceability from one end of the supply chain to the other.
Launched in April 2022, the In-Sight 2800 vision system has been designed to solve complex classification applications. Other tools are currently under development and should be available in the coming months.