A growing global competitive landscape and evolving customers’ expectations are driving manufacturers to invest new capital in modern technology. Along with artificial intelligence, deep learning, businesses are also embracing machine vision as the fourth industrial revolution takes firm hold in manufacturing processes.
Machine vision is literally the ability of a computer to see and process information about what it sees. It relates to all industrial and non-industrial applications in which a combination of hardware and software provides operational guidance to devices in the execution of their functions based on the capture and processing of images. It is similar in complexity to voice recognition – the ability of a machine or program to receive and interpret dictation or to understand.
It is important to make the distinction between machine vision and computer vision although they are overlapping technologies. A machine vision system requires a computer and specific software to operate while computer vision doesn’t need to be integrated with a machine. It is also different from machine learning in that the latter is an application of artificial intelligence that provides data the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning can be used to program machine vision systems in some areas.
Desmond Moru, Computer Vision and Robotics Department, CEIT-1K4 Research Alliance, TECNUN SCHOOL of Engineering University of Spain, uses the example of a fill-level inspection system at a brewery to define machine vision.
“Each bottle of beer passes through an inspection sensor, which triggers a vision system to flash a blinking light and take a picture of the bottle. After acquiring the image and storing it in memory, the vision software processes or analyzes it and issues a pass/fail response based on the fill level of the bottle. If the system detects an improperly filled bottle i.e. a fail, it signals a rejection of the bottle. An operator can view rejected bottles and ongoing process statistics on a display simultaneously.”
How it works
By using one or more video cameras, analog-to-digital conversion (ADC), and digital signal processing (DSP), a machine vision system produces data that gets sent to a computer or robot controller. The data sent is based on the set-up process, whereby one “teaches” the machine-vision system, defining what is good or bad, or outside of limits. The camera/computer visually looks at a part and is programmed to indicate whether the process should proceed, stop, or adjust. If it is outside of boundaries, the program is triggered to throw up a flag.
A few global manufacturing facilities have used machine vision systems since the 1950s, but it began to expand in the 1980s-1990s.
A BCC Research data gives an idea of how big the space is, by pegging the global market for machine vision system components at $19.0 billion for 2016 and an estimated $30.8 billion by 2021.
For Nigeria manufacturers’ spend on technology has often competed with the rising cost of production and foreign exchange volatility. The bulk of the manufacturing establishment in Nigeria is located in the urban area with epileptic national power supply, whereas, the source of the raw materials which is the rural areas are devoid of essential facilities and poor road networks for the easy conveyance of raw materials to the urban centres. The result is the high cost of production.
However, recent technological advances in the country such as mobile phone and broadband penetration as well as increased spending on infrastructure development have seen manufacturers begin to inject more capital in improving their technology.
“I am sure machine vision is the next big thing,” Moru told BusinessDay.
One major advantage of machine vision is quality control in the delivery of certain products and services. Integrating a machine vision system on a production line can enable companies to inspect hundreds, or even thousands, of parts per minute.
“Where the human vision is best for qualitative interpretation of a complex, unstructured scene, machine vision excels at quantitative measurement of a structured scene because of its speed, accuracy, and repeatability,” Moru said. “Without questioning, technology has advanced the service and communication sectors a great deal, in major cities in Nigeria. However, there is still a lot to be done. If you look into the industrial sectors, you would observe that there are already some levels of quality control inspection going on, even only at a small scale and manual. The benefits of machine vision inspections are limitless.”
While machine vision integration may require some hefty capital, but considering the loss of revenue manufacturing companies incurs due to poor quality services, companies will benefit more from an improvement in this area. However, not every machine vision application is capital intensive.
Already most companies are carrying out some level of inspection processes before products are dispatched for public utilization. The difference is in the degree of detail. What a human eye will not easily see, a machine can spot. Moru suggests being open enough to consider and discuss what kind of quality control inspection that should be applied for every process.
“A machine vision system built around the right camera and optics can easily object details too small to be seen by the human eye,” Moru said. “These camera and software are affordable.”
For companies just starting the journey, Moru recommends taking small steps. In terms of sourcing local talents, Nigeria is one of the laggards. However, the new School of Science and Technology of the Pan Atlantic University (PAU) is positioning itself to breach the gap between the academic world and the industrial sector. It will be the first school to groom such talents in West Africa.
Moru who is part of those championing that project says PAU plans to incorporate engineering students into the industrial streamline right from the start of their academic careers so that by the time they are graduating, they would be well prepared to face the challenges of the industry.
“I think that this form of education exposes both the academic institution and the industrial sector to a new world, and hence can wage possible ways for collaboration, research and investigation, which most times industries lack time for, even when they have the resources. My experience doing research at the CEIT-IK4 research center at the University of Navarra, Spain fills me with the conviction that things can improve in Nigeria. Machine vision applications in the industries imply low cost, accepted accuracy, high robustness and speed, high reliability and stability in comparison with manual industrial inspection processes,” he said.
