Cameras and components that make up factory machine vision

Given the size and variety in the manufacturing segment, there are several different kinds of devices used to achieve machine vision in this vertical. This ranges from simple daylight cameras to thermal and other more sophisticated, specialized devices.  

“Today we use a variety of high resolution, high-speed monochrome and color cameras for many different assemblies and inspection ​

applications,” Rick Brookshire, Director of Product Development at Epson America, explained. “These same cameras are used across many verticals including automotive, medical, electronics, consumer products, and many others.”

High precision is a critical element when assembling many parts today. Imagine products like cell phones, watches, or any other electronic devices. The components continue to get smaller thus requiring more precision to assemble them. High precision vision-based robot placement is becoming more commonplace for many applications.

The ingredients in the solution

The major components of a machine vision system include the lighting and lens (optics), image sensor, vision processing, and communications. Lighting illuminates the part to be inspected allowing its features to stand out so they can be clearly seen by the camera. The lens captures the image and presents it to the sensor in the form of light. The sensor converts the light into a digital image which is then sent to the processor for analysis using rule-based software algorithms or deep learning technology. 

Shweta Kabadi, Senior Director and Business Unit Manager of Vision SW and Accessories at Cognex, gave a list of the major camera types and lenses used in factories.
 
“There is a range of vision systems and vision sensors with modular lights, lenses, and filters that can be customized for specific industrial applications,” Kabadi said. “Broadly speaking, the different types include 1D Vision Systems, 2D Vision Systems, Line Scan or Area Scans and 3D Vision Systems.”
 
1D vision: 1D vision analyzes a digital signal one line at a time instead of looking at a whole picture at once, such as assessing the variance between the most recent group of ten acquired lines and an earlier group. This technique commonly detects and classifies defects on materials manufactured in a continuous process, such as paper, metals, plastics, and other non-woven sheet or roll goods.

2D Vision: Most common inspection cameras perform area scans that involve capturing 2D snapshots in various resolutions. Another type of 2D machine vision, known as line scan, builds a 2D image line by line.

Area scan vs. line scan: The term line scan refers to the feature that the imaging device is not taking a snapshot all at once (“area” imaging). The device captures only a thin “slice” or single “line” of image information and either processes that linear data (not common) or combines many lines into contiguous rows of a standard image for subsequent processing.  

“In certain applications, line scan systems have specific advantages over area scan systems,” Kabadi continued. “For example, inspecting round or cylindrical parts may require multiple area scan cameras to cover the entire part surface. However, rotating the part in front of a single line scan camera captures the entire surface by unwrapping the image. Line scan systems fit more easily into tight spaces for instances when the camera must peek through rollers on a conveyor to view the bottom of a part.”
 
Line scan systems can also generally provide much higher resolution than traditional cameras. Since line scan systems require parts in motion to build the image, they are often well-suited for products in continuous motion.
 
3D vision: 3D machine vision systems typically comprise multiple cameras or one or more laser displacement sensors. Multi-camera 3D vision in robotic guidance applications provides the robot with part orientation information. These systems involve multiple cameras mounted at different locations and "triangulation" on an objective position in 3-D space. 

Where visual cameras fail to do the job, thermal cameras come into play. Anupriya Balikai, MD of Spookfish gave the example of the pharmaceutical and food & beverage industry, where sealed products need to be inspected for any leakage or contamination. Visual cameras cannot see beyond the bottle cap, but thermal cameras can be used to check if there is a difference in temperature and this correlates to the sealing patterns.