Due to strict compliance regulations, packaging for medical products must be correctly labeled before it is delivered to customers. For this purpose the Chinese company Shenzhen Jiangrun Xuneng Technology has developed a sophisticated machine vision solution that automatically reads character codes using OCR. The heart of the application is the standard machine vision software MVTec HALCON. This enables the customer to increase the efficiency of the inspection processes and significantly improve product quality.
Production processes in the pharmaceutical industry are subject to particularly strict legal regulations. According to Good Manufacturing Practice (GMP), products must be manufactured to consistently high quality standards. Accordingly, the guidelines impose strict requirements on the documentation of workflows and the inspection of goods. Regular checks are intended to ensure maximum safety and efficacy of the products.
The global health and food company H&H Group is also directly affected by GMP: in order to reliably comply with the regulations, the manufacturer must correctly label the packaging of its medical and cosmetic products. For this purpose, various information such as batch number, date of manufacture, and expiration date are printed on the cartons. The character combinations must be correct and complete. This is the only way to ensure that products can be correctly identified and that quality requirements with regard to labeling are consistently met. It is therefore essential to check the character codes carefully before the cartons leave the factory and are delivered to customers.
Inadequate controls led to complaints
Until now, this control process at the H&H Group was carried out purely manually, which proved to be very costly and time-consuming. Due to the high number of packages and the fast cycle rate, inspection could often only be carried out on a random basis. In some cases, this led to incorrectly labeled products being delivered to wholesalers and other customers. As a result, complaints and grievances piled up, leading to financial losses, customer losses, and serious damage to the company's image.
In order to improve the quality of product labeling, the inspection process had to be made more efficient. To this end, the managers at the H&H Group commissioned Shenzhen Jiangrun Xuneng Technology to develop an appropriate solution. The company specializes in 2D and AI software frameworks that focus primarily on 2D and 3D vision solutions, including localization, identification, and measurement of objects. The provider focuses on a wide range of industries, such as food, medicine, chemicals, packaging, automotive, and rail transport.
Machine vision platform automates visual inspection
Shenzhen Jiangrun Xuneng Technology has developed a machine vision platform that enables the visual inspection of product labels on packaging to be fully automated. The letter-number combinations are read and checked using modern optical character recognition (OCR) technologies. "This application presented us with major challenges. The characters printed on the cartons are usually encrypted, with different types and sizes of codes combined. The characters are often not located exactly where they should be, but are offset. In addition, the letters and numbers are often printed incorrectly, unclearly, or blurred on the packaging, which can lead to problems in clearly recognizing the codes," explains King Wang technical application engineer at Jiangrun.
Another challenge is the fast cycle rate of the inspection workflow. The characters must be read and checked at high speed in order to achieve maximum product throughput. This requires comprehensive preprocessing by the OCR algorithms. This is the only way to reliably find the respective target point, ensuring the highest possible recognition accuracy even with different types and sizes of characters.
MVTec HALCON ensures precise identification and localization of characters
Jiangrun's machine vision platform allows these complex requirements to be addressed with precision. The standard machine vision software products MVTec HALCON, which form the heart of the solution, are used for this purpose. The HALCON algorithms are used for pre- and post-processing of the images as well as for the precise identification and localization of characters. The software must first precisely recognize the character background in the image and find a horizontal reference line to determine the exact position of the characters. In the process, a region of interest (ROI) is defined within which the numbers and letters, such as an expiration date or batch designation, are recognized, read, and checked. By comparing them with reference characters, errors in the labeling can be reliably detected.
Dynamic OCR with high stability and speed
"Thanks to MVTec HALCON, we were able to significantly shorten the project cycle, reduce the costs for development, operation, and maintenance of our machine vision platform, and significantly improve the efficiency of implementation. In addition, we are able to implement dynamic optical character recognition with high stability and processing speed. New types of products, markings, or fonts can also be flexibly added to the application. This allows us to optimize OCR inspection, cover a wide range of different character specifications, and achieve good results even with display errors or incorrectly positioned characters," says King Wang.
The end customer also benefits from the machine vision platform powered by MVTec HALCON: The H&H Group can automate the entire inspection process and relieve its employees of tedious manual work. This improves the efficiency of inspection workflows and maintains the quality of product labels at a consistently high level. As a result, the number of customer complaints is reduced to a minimum and the brand's image is significantly enhanced.
Further applications with MVTec HALCON are planned
Based on the successful collaboration, Jiangrun plans to implement further image processing applications with MVTec HALCON in the future: "We have a range of standard software frameworks that use HALCON to implement machine vision functions. This enables us to realize complex image processing projects for our customers much more easily and efficiently. I would like to mention the intensive exchange with our MVTec colleagues in China. Their professionalism, technical advice, and training helped us to implement the project quickly," concludes King Wang.