Skip to main content

How Deep Learning Improves Machine Vision in Factories

Factory automation is evolving, once again. Machine vision technology remains popular in the manufacturing environment, due to its proven track record of results. However, the introduction of artificial intelligence (AI) technology and machine learning applications will transform many conventional factories.

The emergence of deep learning apps creates expanded capabilities and flexibility, leading to more cost efficiency and higher production yield. Deep learning-based machine vision techniques within smart manufacturing will experience a CAGR of 20 percent between 2017 and 2023, with revenue that will reach $34 billion by 2023, according to the latest market study by ABI Research.

Machine Vision Market Development 

Manufacturers need to improve their production yields and workflow efficiency. Legacy machine vision is easy to implement but is somewhat limited. Current solutions that are widely deployed in quality control, safety inspection, predictive maintenance, and industrial monitoring rely upon preprogrammed rules and criteria, supporting limited ranges of functions.

In contrast, AI deep learning-based machine vision is highly flexible due to its ability to be trained and improved using a new set of factory data, enabling manufacturers to incorporate updates and upgrade quickly.

"This is in part driven by the democratization of deep learning capabilities. The emergence of various open source AI frameworks -- such as TensorFlow, Caffe2, and MXNet -- lowers the barrier to entry for the adoption of deep learning-based machine vision," said Lian Jye Su, principal analyst at ABI Research.

These AI frameworks can be deployed using on-premise IT infrastructure and vendor software suites. In the past, the choice of machine vision solutions was limited to a handful of companies that performed relatively simple image processing operations. With deep learning-based machine vision, manufacturers can now develop their own deep learning-based machine vision systems.

In addition to cameras, deep learning-based machine vision can also incorporate data collected from various sensors, including LiDAR, radar, ultrasound, and magnetic field sensors. The rich set of data will provide further insight into other aspects of production processes.

Compared to conventional machine vision, which can only detect product defects and quality issues which can be defined by humans, deep learning algorithms can go even further. These AI algorithms can detect unexpected product defects, providing flexibility and valuable insights to manufacturers.

According to the ABI assessment, manufacturers are encouraged to work with a wide range of vendors, including industrial cloud platform, camera and sensor suppliers, and public cloud vendors. Deep learning-based machine vision requires a robust cloud platform that will enable condition-based monitoring, sensor data collection, and analytics.

Outlook for Machine Vision Application Growth

Unlike conventional machine vision which relies on line-by-line software coding, deep learning-based machine vision models can be deployed by users without significant developer experience, as these models undergo unsupervised learning based on data gathered.

"Manufacturers are opening up to adopting AI capabilities into their workflow. Deep learning-based machine vision will serve as the right catalyst to drive progress. Startups that launch as deep learning-based machine vision solution providers are also beginning to enable big data processing, process optimization, and yield analytics on their platform," concluded Su.

Popular posts from this blog

Mobility-as-a-Service Creates Disruptive Travel Options

Building on significant advances in big data, analytics, and the Internet of Things (IoT), more innovative transit service offerings aim to increase public transport ridership and reduce emissions or congestion within metropolitan areas. By providing these services through smartphone apps, the transit services also significantly increase user convenience, providing information on different human mobility offerings -- including public transport, ridesharing, and autonomous vehicles. Mobility-as-a-Service Market Development According to the latest market study by Juniper Research, Mobility-as-a-Service (MaaS) subscribers will generate $53 billion in revenue for MaaS platform providers by 2027 -- that's rising from $5.3 billion in 2021. Let's start with a basic definition. MaaS is the provision of multi-modal end-to-end travel services through single platforms, by which users can determine an optimal route and price. The study identified a monthly subscription model as key to incr

Robocall Mitigation Solutions to Halt Criminal Threats

If you answer the phone and hear a recorded message instead of a live person, it's likely a robocall. A robocall is a phone call that uses a computerized autodialer to deliver a pre-recorded message. In 2020, the U.S. Federal Trade Commission (FTC) received 2.8 million consumer complaints about robocalls. Offering solutions to robocalling and associated fraudulent business practices, computerized mitigation platforms are an integral part of the solution. Platforms that are focused on actionable systems to disrupt unsolicited and potentially criminal phone calls help telecom service providers and industry regulators. Issues of whether one-size-fits-all developments are sufficient to be effective across the spectrum need to be addressed, and whether a single telecom network operator working unilaterally with a third-party platform could compromise desired or mandatory industry-wide standards. Robocall Mitigation Market Development According to the latest worldwide market study by Jun

Secure Digital Workspace Apps Enable the Future Enterprise

In early 2020, as the world responded to the COVID-19 pandemic disruption, many organizations were forced to rapidly transform their communications networks and IT infrastructure to support an unprecedented shift to remote work. Before the pandemic, approximately 38 percent of employees were remote full-time or had a flexible work arrangement where they split time between home and office locations. During the pandemic, the percentage of remote workers that CIOs had to support reached almost 72 percent. Future Enterprise Technology Market Development Enterprise leaders have been forced to adapt to a new state, shifting from traditional office-based operations to distributed workforce environments that must still provide the same level of connectivity, security, and efficiency across the organization. According to the latest worldwide market study by International Data Corporation (IDC), addressing connectivity across geographies and transforming networks to become more virtual and agile