With the advent of Industry 4.0, machine vision is playing an increasingly important role in the field of intelligent manufacturing. In order to enable more users to acquire basic knowledge about machine vision, including how machine vision technology works and why it is the right choice for achieving process automation and quality improvement, we need to provide more information.
We've prepared this article of useful information on machine vision for you!
What is machine vision?
Let's start with the definition of machine vision. According to the Society of Manufacturing Engineers, machine vision is the use of optical non-contact sensing devices to automatically receive and interpret images of real-world scenes to obtain information for controlling machines or processes.
So, what does this actually mean? Simply put, machine vision is the automatic extraction of information from digital images for process control or inspection of manufactured products. To better understand machine vision, let's take a gypsum board defect detection system as an example:
Paper hole detection: When the paper is in motion, a high-speed camera captures images of the paper in real time and transmits the captured images to a computer. The vision software running on the computer analyzes the captured paper images using certain image processing algorithms. If a hole is detected, an alarm is triggered based on the set hole area.
Vertical edge detection: Using a linear laser as an auxiliary device, an industrial camera captures images of the vertical line. The images are then processed by a computer to calculate the verticality of the gypsum board facade based on the line's inclination, and the angle at which it is not perpendicular. When the vertical edge angle exceeds a set range, a motor-controlled edge-shaping device achieves closed-loop control. The operator can view data such as the area of holes in the gypsum board and the vertical edge angle on a display screen.
For example, determining spark plug gaps or providing positional information can guide robots to align components during manufacturing and assembly. The example shown in Figure 2 mainly illustrates how machine vision systems can be used to detect whether an oil filter (right) passes or fails, and to measure the width of the central shaft head on the bracket (left).
▲Machine vision systems can perform real-time measurement and inspection on the production line, such as processing brackets (left) or oil filters (right).
In this application example, the fill level inspection system can only provide two results, which demonstrates the characteristics of a binary system:
1. If the product is qualified, the test result will be "pass".
2. If the product is not up to standard, the test result will be "failed".
What are the advantages of machine vision?
While human vision excels at qualitatively interpreting complex, unstructured scenes, machine vision, with its advantages in speed, accuracy, and repeatability, is adept at quantitatively measuring structured scenes. For example, on a production line, a machine vision system can inspect hundreds or even thousands of components per minute. Equipped with cameras and optics of appropriate resolution, machine vision systems can easily examine details of objects too small for the human eye to see.
Furthermore, by eliminating direct contact between the inspection system and the inspected components, machine vision can prevent component damage and avoid the maintenance time and costs associated with mechanical component wear. By reducing human intervention in the manufacturing process, machine vision also offers additional safety and operational advantages. In addition, machine vision can prevent cleanroom contamination by human intervention and protect workers from hazardous environments.
Application areas of machine vision
Identification
Decoding standard 1D and 2D barcodes
Optical Character Recognition (OCR) and Authentication (OCV)
Detection
Color and defect detection
Inspection of the presence or absence of parts or components
Target position and orientation detection
Measurement
Size and capacity inspection
Measurement of preset markers, such as the distance between holes.
robotic arm guidance
Output spatial coordinates to guide the robot arm to precise positioning
