Forward-thinking manufacturers are increasingly turning to the capabilities provided by Artificial Intelligence (AI), specifically a subset of machine learning called deep learning, in their machine vision applications. Machine vision solutions are not new. These industrial hardware and software have been around a while.
The benefits of machine vision are seen clearly in industries that require higher levels of safety, quality, compliance and efficiency at speed, including automotive, food and beverage, pharmaceutical, and electronic manufacturing.
Machine vision applications are used for quality/end of line inspection, traceability of parts across the supply chain, measurement, presence/absence, metrology and porosity inspection. However, the operational challenges around older machine vision systems also remain.
These include hardware and software compatibility, financial costs, procurement times, maintenance, interoperability, training and handling complex use cases. For manufacturers in Germany, industry challenges around hiring enough skilled labour is also becoming a higher priority issue. Automation is increasingly filling labour gaps and supporting the existing workforce.
Leverage deep learning for machine vision
Setting up and managing industrial automation inside a manufacturing plant, for example, is often slow and difficult due to the reliance on multiple devices with different software and old, antiquated user interfaces. Many vendors also require customers to use different software for fixed industrial scanners and machine vision cameras, which makes it all hard to navigate and costly. That runs counter to the core principles of scalability, longevity and compatibility that we apply across all portfolios, especially our mobility, scanning, and automation platforms.
Manufacturing industries have evolved. Production volume and speed keep going up, new safety and regulatory compliance measures must be met, the volume of data grows and needs to be sifted and turned into useful business insights. Manufacturers need modern machine vision solutions that can meet these challenges.
But there are still many in the industry who are unaware of the new range of deep learning-powered machine vision solutions, or have not yet understood how they can benefit their inspection and measurement workflows.
Eighty one percent of automotive decision-makers say they could better meet business objectives if their organisations made more investments in technology, while 78% believe their organisation needs to be more innovative to remain competitive in the automotive industry. However, eight in ten (78%) agree their organisations struggle to keep up with the speed of technological innovation.
Increased automation, including automation of visual inspection using machine vision, can unlock greater accuracy, speed, compliance, and safety. It also means front-line engineers can hand over inspection tasks to machine vision, leaving them more time for other valuable and needed workflows.
More powerful, flexible, and easier to use
Machine vision software powered by deep learning is an exceptional solution for surface inspection, inspection of raw materials with naturally occurring variations, textile inspection, classification, conformal coating inspection, segmentation, and feature and anomaly detection.
The right combination of hardware and software leveraging deep learning can enhance machine vision applications, including more complex use cases, as well as enhancing the role of the engineer to think and act more like a data and AI specialist. Newer cameras, sensors and machine vision platforms with deep learning can help overcome longstanding challenges that older machine vision systems are not equipped to face.
Today’s AI-powered machine vision tools come with user-friendly ‘drag and drop’ interfaces, readymade tools and libraries, and flow-chart approaches to creating solutions, with support from experienced machine vision technology partners who can provide the advice and data quality and labelling guidance needed.
They also offer users flexible upgradability: fixed industrial scanners can be upgraded to machine vision cameras with a simple license that upgrades industrial scanning software into machine vision software platforms, creating cost and time savings and flexibility to meet demand.
Engineers, programmers and data scientists can collaborate with graphical environments equipped with comprehensive sets of thousands of proven and ready-to-use filters for the creation of sophisticated vision applications, and programmer libraries for customised code and integrations using C++ code generators and thousands of functions for image analysis applications.
Flexibility and ease of use can be seen in the hands of engineers on the plant floor. For example, many of the applications listed above – end of line, traceability of parts, presence/absence – could require Optical Character Recognition (OCR), so getting it right is important. OCR isn’t a new technology. It’s been around for a long time and is a familiar tool for reading barcodes, serial numbers, lot numbers, and Vehicle Identification Numbers (VINs), to ensure the correct components and parts are in the right place at the right time for the right model of vehicle.
However, the problems using OCR are also familiar. They need a lot of training time, can be unstable when faced with a change in environment, and don’t handle complex use cases well. Many OCR tools require manufacturers to invest a lot of time for something that is at best ‘okay’ and struggles to read obscure and damaged characters, engraved and embossed formats, characters on reflective and curved surfaces, or changing and harsh lighting conditions.
The latest OCR tools powered by deep learning use a neural network that mimics the human brain. These newer tools deliver very high accuracy straight out-of-the-box and work on both NVIDIA GPU and CPU. They can handle complex use cases, eliminate training time and ensure stability and ease of use, even for a non-expert. This new deep learning OCR comes with a ready-to-use neural network that is pre-trained using thousands of different image samples.
This enables the user to create a robust OCR application in just a few simple steps. Deep learning OCR can also offer a flexible ‘deep learning everywhere’ experience for industrial imaging professionals – on desktop PCs, whether Windows, Linux or Linux ARM, on Android handheld devices, and smart cameras.
Stay ahead of the curve
Manufacturing leaders are already using deep learning to gain a competitive edge in the face of industry and customer needs. In addition, discussions continue around the possible deficit of skilled labour, which is impacting a range of industries. Labour hiring challenges could prove another driving focus leading to greater use of machine vision, in order to maintain operations and support the current workforce.
A recent global survey of original equipment manufacturers in the automotive industry found that 24% are using machine vision today, with 44% planning to use it by 2027. That’s a significant 83% increase. A 70% jump was seen between current (27%) and future use (46%) of machine learning.
Do not wait for industry peers and competitors to lead the way and avoid being purely reactive to industry challenges. Now is the time to capitalise on deep learning machine vision.
You can learn about Zebra’s modern, cutting-edge machine vision portfolio here. To discuss these issues, reach out to Stephan Pottel directly.
About the author
Stephan Pottel: EMEA Practice Lead, Manufacturing , Transportation & Logistics | Zebra EMEA
Stephan Pottel has 20+ years of industry experience in bringing new technologies to early adopter customers across the Transport, Logistics and Manufacturing verticals. He has been with Zebra since 2017 as part of the EMEA Strategy and Business Development team and is looking after trends and key market drivers in the Automotive industry. He holds a bachelor’s degree in Applied Computer Science from the University of Applied Sciences Niederrhein in Germany.
