Ask the Expert: What is the Difference Between Machine Vision and Computer Vision?

And what is the correlation between fixed industrial scanning and machine vision? We ask an expert to shed light on these hot industrial automation trends.

A fixed industrial scanner is used to scan barcoded boxes as they move down a conveyor belt in a warehouse.
by Your Edge Blog Team
May 18, 2021

Many supply chain organizations are exploring the potential of more automated and intelligent technologies right now, Zebra included. With ever-changing production goals and tighter order fulfillment timelines, manufacturers need easy-to-use solutions that help elevate quality and drive production performance. Warehouse and distribution center operators are looking for ways to streamline the returns process. And retailers are constantly seeking tools that take the burden of increased fulfillment demands off workers, without compromising the quality of the customer experience.

That’s why there’s growing buzz around technologies such as machine vision and computer vision.

But despite their similar-sounding names, these technologies have two very different purposes which, at times, do converge. There are also technologies, such as fixed industrial scanners, that can work in tandem with machine vision and computer vision solutions to bring more breadth, depth and speed to operational visibility and industrial automation. So, we’ve asked Donato Montanari, Vice President and General Manager of Zebra’s Machine Vision business, to break down the terminology and uses cases in the latest installment of our “Ask the Expert” series:

Your Edge Blog Team: Can you start by explaining the differences between machine vision and computer vision?

Donato: It might be easiest to start with the similarities. Machine vision and computer vision are both intelligence-based systems used for image capture, processing, and analysis. In enterprise and industrial environments, their shared value lies in their ability to improve quality control and process control by catching both isolated issues and patterns that a human might miss for whatever reason. For example, both machine vision and computer vision systems are trained to look for discrepancies within some component of an operation. When issues are identified, the systems will notify key stakeholders and then help them decide what steps to take to avoid incurring significant inventory, financial or customer losses.

However, the speed and level at which this intelligence is gathered, distributed and applied is one of the most distinguishing factors between the two types of technologies.

Machine vision is often used on a production line in a manufacturing facility to look for visual inconsistencies in a label, package or even item design that could lead to returns, noncompliance penalties, and other costly consequences. Many use a pass/fail alert structure to help inspectors quickly decide whether items are cleared to continue down the line or should be removed without having to consult with others first. Machine vision systems also tend to be self-contained, meaning the image capture and analysis occur right there on the line – data doesn’t have to be sent to a back-office system for processing.

Computer vision, on the other hand, is often used as a back-end processing platform for image capture technologies used on the front lines, such as intelligent automation solutions, bioptic scanners, and even mobile computers. Advanced algorithms are used to help decision makers see what’s happening within their operations and fully understand why it’s happening. Though computer vision still elicits fast decision making and action, there tends to be a little bit longer lead time between the two given the depth and breadth of data being processed through the system. Computer vision is typically a far more comprehensive analysis tool than machine vision, which is much more comparative at a single factor level (i.e., the text on the item’s warning label is supposed to be red but the machine vision camera indicates that it’s purple.)

In fact, machine vision systems tend to be designed to support very specific industrial automation applications due to their unique line of sight capabilities – and limitations. Computer vision algorithms, on the other hand, can be used more broadly to support qualitative analysis needs. That’s why you’re more likely to see machine vision or some derivative – such as fixed industrial scanning – in manufacturing, warehousing, and distribution environments, and computer vision in retail or healthcare.

Your Edge Blog Team: So, is machine vision essentially a camera solution?

Donato: Yes and no. Machine vision relies on highly specialized camera technology to reconcile an item or label’s current visual state with what it should look like per the standards guide. However, when someone talks about machine vision, it’s unlikely he or she is referring exclusively to the camera component. “Machine vision” is actually a cohesive set of technologies and methodologies that are used for the automatic, imaging-based inspection and tracking of work-in-progress items and finished goods from a process control and quality control perspective.

For example, an automotive supplier might use machine vision to improve the speed and accuracy of visual inspections as items move down the line in a discrete manufacturing environment where quality control is critical. The machine vision system – meaning the smart cameras or sensors – positioned either overhead or in line with the conveyor belt can learn to recognize when a part is mislabeled or there is a discrepancy in the design when compared to the blueprints. After capturing a snapshot, an intelligent analysis will occur on the spot to verify the quality of what’s being produced and prepped for shipment. If multiple anomalies are identified by the machine vision system, that could be indicative of a larger process issue that the manufacturer may not have otherwise recognized until after parts were shipped to – and returned by – the customer.

Your Edge Blog Team: Can machine vision cameras be used to track and trace items, then?

Donato: Fixed industrial scanning solutions are utilized more for the track and trace of parts or finished goods as they move down a production, picking, packing or shipping line, whereas machine vision is used most often for the visual inspection of such items for quality control or process control purposes. However, fixed industrial scanners – at least the ones Zebra offers – can be used for machine vision with a fairly simple software reconfiguration.

Your Edge Blog Team: Can you clarify what you mean by track and trace in this case?

Donato: Fixed industrial scanners are typically used to read the barcodes on items moving along conveyor belts or order fulfillment lines in distribution centers and warehouses and provide a status update to logistics managers or possibly even customers. In addition to verifying that an item has passed by a checkpoint, which is the tracking component, these scanners might be set up to verify the accuracy of product or package labels, automatically confirm that all items in an order have been picked and passed along for packing, or even facilitate shipment routing. Fixed industrial scanners can also be used to verify returned items and help expedite the reshelving process. If configured for machine vision, these scanners could even be used to identify items that aren’t acceptable for return per quality standards defined in the system.

At the end of the day, logistics managers and quality control teams just want a good tool to help decode items coming down the line more quickly than is possible today. Any technology that can help eliminate the quality issues and fulfillment errors that cost them time, money and – in some cases – customers is also much appreciated.

Your Edge Blog Team: Is that why Zebra decided to develop a new lineup of fixed industrial scanning and machine vision solutions?

Donato: That is certainly a key driver. Customers are always motivating us to innovate, and we’re proactively exploring ways in which technology can be better designed and utilized to address their pain points.  Zebra has a strong heritage in data capture, proven success with track and trace solutions, and a number of high-performing inspection technologies within our existing portfolio. Even more than that, we understand what is required technologically speaking to get data to the right place at the right time​ to maximize its value.

While 88% of manufacturers say they are capturing data about their assets and operations, only 18% believe they are fully equipped to deliver on the Internet of Things (IoT) and connect that data to their business systems to improve operations. Many warehouse and distribution center operators share the same frustration and challenge. So, Zebra has worked diligently to deliver solutions that help automate the collection, analysis and application of all kinds of data in a simple way.

Fixed industrial scanning and machine vision solutions, which are natural extensions of our existing portfolio, fill a gap in customers’ needs that can’t be addressed as effectively by the other automation solutions. And they’re both key to improving productivity and efficiency and mitigating quality issues that could challenge an organization’s ability to meet demand.

Your Edge Blog Team: Fixed industrial scanners and machine vision have been around for a while, though. Why did Zebra feel now was the right time to enter this category?

Donato: We’re continuously monitoring the market and, more specifically, the performance of all technologies our customers utilize across their operations. As you noted, these aren’t new technologies. The math and science behind machine vision actually dates back to the 1930s. However, customers and partners have repeatedly told us in recent years that most machine vision solutions are complex and hard to use. 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 figure out, 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.

That’s why we decided to design our fixed industrial scanning and machine vision solutions to run on the very same software platform, which we call Zebra Aurora™. This ecosystem approach gives customers a toolset that can immediately improve their ability to track and trace items throughout their automation processes with trusted decode performance. And, at the same time, it provides them with a logical upgrade path that helps them access more features and unlock value as needed without the complexity typical for these types of solutions. The extreme flexibility, versatility and scalability of both the hardware and shared software platform gives customers a natural stepping stone from fixed industrial scanning to machine vision.

This type of innovation takes time. However, many of our customers and partners are excited that we did take the time to engineer these new solutions. They provide a level of simplicity not found with other fixed industrial scanning and machine vision systems from an implementation, handling and management perspective. These new solutions are very easy to learn and run.

Your Edge Blog Team: So, Zebra’s fixed industrial scanning and machine vision systems both leverage Aurora?

Donato: Yes, there is one software platform powering the entire product family. In fact, three out of the four scanning devices in this new portfolio can be used for either fixed industrial scanning or machine vision. So, customers don’t have to rip and replace hardware every time they want to expand or add on applications. They can easily configure the devices for either fixed industrial scanning or machine vision – or repurpose for either use case – using the same Zebra Aurora software​ platform. This drastically reduces the time and training required to onboard new applications, as well. Once operators learn how to use the hardware and software, it’s easy to transition that knowledge and skill set to new use cases. The commands on the devices and overall system structure aren’t changing. Plus, you don’t actually have to be a machine vision expert to use our system, like you do with many others. It has a very intuitive user interface, and the software platform streamlines the vision inspection process in a way not matched by any other offering on the market to date.

Your Edge Blog Team: What has the feedback been from customers thus far?

Donato: Those who had the opportunity to see the solutions under NDA are very excited about the ability to transform a fixed industrial scanner into a comprehensive machine vision solution as needed to meet evolving operational, market and compliance requirements. The highly fragmented and complex nature of industrial automation, in general, has turned off manufacturers and supply chain organizations from technologies that – if designed and executed the right way – could really have a positive impact on their businesses. We’re confident that our solutions are addressing a decades-old pain point for our customers and the broader market.

###

Editor’s Note:

To learn more about how you can use new advancements in machine vision to transform your manufacturing and logistics operations, download this free white paper.

null
Your Edge Blog Team
We want to hear from you! Submit your comments, questions and topic ideas to blog@zebra.com.
Want Our Bi-Weekly Blog Roundup?

Subscribe to Zebra's Blog

Prefer Real-Time Notifications?

Get the RSS feeds

Search the Blog
Are You a Zebra Developer?

Find more technical discussions on our Developer Portal blog.

Reflexis is Now Part of Zebra Technologies

Visit the Reflexis blog for more retail, hospitality and banking-related insights.