Trends and drivers for machine vision technology

Machine vision is heating up. It can perform more tasks than ever before, and do them better. Here is how machine vision is impacting packaging.

1. When size goes down and power goes up, performance benefits. Due to miniaturization and advances in the power of digital signal processors (DSP), imaging sensors, and decoding algorithms, traceability applications such as ID code reading, text verification, label inspection, and mark quality assessment can now be accomplished more economically by inspection systems.

2. New requirements are driving new technology. Facing increased regulations in the coming years to fight counterfeiting and improve food and drug safety, major pharmaceutical and food manufacturers have put traceability at the top of their agenda. Most of them uniquely code each lot or batch to identify time and location of production to make recalls more efficient and less costly. But this is not sufficient to meet the increased regulations of the future that will involve traceability, serialization, and authentication requirements.

Whether implementing traceability at the batch level or using serialized packaging to support full traceability (for initiatives such as e-pedigree in the pharmaceutical industry or other regulatory requirements), producers must deploy a broad range of technology and software platforms, spanning all levels, processes, and systems. At the highest levels, enterprise systems typically interface between the supply chain and plant-level systems; at the machine level, inspection system technology is used for applications such as bar-code reading, text verification, mark quality assessment, label inspection, and general machine vision functions. Beyond supporting compliance, producers are discovering that inspection systems deliver value in being able to stop counterfeiting, prevent parallel trade through unauthorized channels, and achieve greater visibility into how products are made, distributed, and used across supply and value chains.

In the CPG sector, suppliers are adding to this momentum. General Mills, Sara Lee, ConAgra Foods, Kraft Foods, and other major consumers of food packaging have formed the Food Safety Alliance for Packaging (FSAP). This consortium seeks to minimize mislabeling and is largely focusing its efforts on suppliers of labels and direct-print food-contact materials such as carton board and plastic films.

3. The use of vision technology is spreading. Vision is being used in more places throughout the manufacturing process, particularly with the application of small, distributed cameras. By using vision throughout the production process, problems can be identified at the source, reducing waste and cost while improving response time. A snapshot of today’s applications includes:

• Confirming package and product match, lowering risk of recall
• Reducing scrap by detecting wrong or mislabeled products early in production
• Checking for torn or missing labels
• Reading 1D and 2D bar codes, enabling track-and-trace
• Verifying print integrity, ensuring brand imaging on store displays
• Detecting products damaged in operations such as cartoning
• Checking date code presence
• Ensuring that ink-jet printers are functioning properly
• Performing date and lot code OCR and OCV, verifying that product information is correctly printed, and that labels are placed on the right products
• Providing guidance for robotic actuators
• Gauging
• Checking for roundness and conformity
• Providing shape-based orientation

4. The PC-based versus smart camera vision debate continues. Generally, today’s vision systems are divided into two groups: PC-based and smart camera. Key differentiators between the two include architecture, cost, capability, and development environment. The primary architectural difference between PC-based vision systems and smart camera vision systems is one of centralized versus distributed processing. PC-based systems generally multiplex industrial cameras from a single processor to distribute vision at multiple points on the production line. Smart camera systems combine distributed processing with high-speed networking to provide highly scalable systems. Both approaches have advantages. PC-based machine vision systems provide great flexibility in the number of options users can select (e.g., line scan or area scan camera). They are easily used with third-party software, and tend to offer more power and speed due to sophisticated processors. PC performance increases with each boost in processor speed, which makes new PC-based vision systems well suited for the most complex or mathematically intensive applications. However, because PC technology changes so rapidly, it’s not as easily replicated as off-the-shelf smart cameras. Smart camera systems cost less to purchase and implement than their PC-based counterparts. They are simpler to operate, maintain, and integrate into the manufacturing environment. As they are less complex than computers, they are also more reliable, with fewer components presenting operational risk.

5. It’s a more colorful, detailed world. The depth of color vision tools is empowering packagers. Newly available color vision systems are “entry-level” in terms of price only. They are not one-tooled sensors, but highly capable smart systems with all the abilities of their monochrome counterparts, plus specialized ones. A further advance is the shift to higher resolution, which is prompting many users to tackle more challenging inspection applications.

6. Simplicity is a priority. Continuing to improve ease of use is something that all companies making inspection systems will continue to focus on. That (and entry-level pricing) is attracting new customers and opening up new applications. User interfaces are being made simpler and easier with icons, multilingual help text, and one-button operations for functions such as learning a product. The more inspection system vendors reduce the learning curve, the more they lower the cost of deployment.

7. The use of Ethernet is accelerating. Inspection systems generate an enormous amount of process information, compared to many other factory-floor devices. As a result, they are one of the driving technologies accelerating the use of Ethernet on the plant floor. Users needed to move the large images and data files, so they turned to Ethernet because most had some in-house expertise with it at the corporate IT level. Today, Ethernet is a key enabler for those using inspection systems on the factory floor. Many systems offer built-in Ethernet networking capabilities that can link multiple sensors across the factory, integrate software for managing inspection activity remotely, and share emerging inspection information at all levels of an organization.

Liked this article? Download the entire playbook here.

Rethinking Packaging Robotics to Prioritize Flexibility
In this eBook, you’ll learn how to guard against the traps that CPGs sometimes inadvertently set for themselves when implementing robotics that lead to automation “brittleness.”
Read More
Rethinking Packaging Robotics to Prioritize Flexibility
Special Report: Track & Trace
Discover new tools to approach the supply chain that allow you to leverage your data, see real-time visibility, and forecast future sales. You’ll also learn about KH Hive, an in-house digital demand planning tool that Kraft Heinz created to help the company realize its goals, forecasting sales expectation down to the SKU level, location level, and daily level.
Read More
Special Report: Track & Trace