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

IoT Device Management Demand Gains Momentum

More forward-thinking CIOs and CTOs are focused on the adoption of the Internet of Things (IoT). Management challenges are top of mind for those who have already deployed a large number of sensors and associated network edge devices. Device management services are evolving in response to a greater breadth of new device technologies such as edge intelligence and related connectivity solutions, as well as the customer scalability and security of IoT deployments. But forward-looking suppliers are also preparing for a world where 41.3 percent of the connected devices will be using some form of Low Power Wide Area (LPWA) technologies by 2026. IoT Device Management Market Development Since IoT customers increasingly need to manage a larger fleet of connected devices, ABI Research now forecasts that IoT device management services will exceed $36.8 billion in revenues by 2026. Standardization is beginning to play a bigger role in device management services, as more connected devices use LPWA t

Anywhere, Anytime Workplace Demand for SASE

The ongoing adoption of flexible working models within the enterprise market has significant implications for typical IT organizations that must now support knowledge workers and front-line employees that operate outside the corporate network perimeter. The global COVID-19 pandemic created IT networking and security challenges. The expansion of the distributed workforce, an increasing reliance on cloud computing infrastructure, and the requirement to securely connect online employees -- wherever they choose to work, at any given moment in time. Legacy IT solutions that have rigid network underlays and a requirement for on-premises infrastructure cannot adequately deal with these trends. This 'Anywhere, Anytime Workplace' led to demand for new Secure Access Service Edge (SASE) solutions, with networking and security delivered as-a-service. Anywhere, Anytime Workplace Market Development   Although converging networking and security capabilities offer enterprises a promising solut

Cloud Edge Computing Demand Continues to Grow

Public cloud computing solutions are moving closer to the edge of networks where CIOs and CTOs are hosting new apps. The edge journey is well underway for forward-looking organizations as they seek to connect with customers, improve operational efficiency, and adopt digital business technologies to drive innovation. The latest worldwide market study by International Data Corporation (IDC) found that three-quarters of organizations plan to increase their edge computing spending over the next two years with an average increase of 37 percent. A combination of factors is driving this increased spending at the edge. Cloud Edge Computing Market Development The performance requirements of expanding workloads and new use cases that leverage artificial intelligence (AI) and machine learning (ML) demand greater compute capacity at the edge. In addition, the amount of data being stored in edge locations are rapidly expanding, and organizations plan to keep this data longer. As a result, the numbe