Popularization of Science: Principle Analysis and Application Field of Machine Vision Technology

Machine vision system refers to the conversion of the captured object into image signal through machine vision products (i.e. image capturing devices, divided into CMOS and CCD) and transmission to a special image processing system, which converts the captured object into digital signal according to the information of pixel distribution, brightness, color, etc. The image system extracts the characteristics of the target by various operations, and then according to the discrimination. The result is to control the device action on the spot.

machine vision

The characteristic of machine vision system is to improve the flexibility and automation of production. In some dangerous working environments that are not suitable for people's work or where artificial vision is difficult to meet the requirements, machine vision is often used to replace artificial vision. At the same time, in the mass industrial production process, using artificial vision to inspect product quality is inefficient and inefficient, and using machine vision detection method can greatly improve production efficiency and automation of production. Moreover, machine vision is easy to realize information integration, which is the basic technology to realize computer integrated manufacturing. It is precisely because machine vision system can acquire a large amount of information quickly, and it is easy to process automatically. It is also easy to integrate with design information and processing control information. Therefore, in modern automated production process, machine vision system is widely used in the field of condition monitoring, product inspection and quality control.

Basic structure

A typical industrial machine vision system includes light source, lens, camera (including CCD camera and COMS camera), image processing unit (or image capture card), image processing software, monitor, communication/input/output unit, etc.

The system can be further divided into: Host Computer, Frame Grabber and image processor, image camera, CCT lens, microscope head, lighting equipment, Halogen light source, LED light source, high-cycle fluorescent lamp source, flash source, other special light source, image display, LC mechanism and control system, PLC, PC-Base controller, precision desktop, servo. Sports platform.

Working principle

Machine vision detection system uses CCD camera to convert the detected object into image signal, which is transmitted to a special image processing system. According to the information of pixel distribution, brightness, color and so on, it is transformed into digital signal. The image processing system carries out various operations on these signals to extract the features of the target, such as area, number, position and length, and then according to the preset permissibility and length. Other conditions output results, including size, angle, number, qualified/unqualified, yes/no, etc., to achieve automatic identification function.

lighting

Lighting is an important factor affecting the input of machine vision system, which directly affects the quality of input data and application effect. Because there is no universal machine vision lighting equipment, for each specific application example, the corresponding lighting device should be selected to achieve the best effect. Light sources can be divided into visible light and invisible light. The common visible light sources are white flag lamp, fluorescent lamp, mercury lamp and sodium lamp. The disadvantage of visible light is whether the energy of light is stable. How to keep the light energy stable to a certain extent is an urgent problem to be solved in the process of practicality. On the other hand, ambient light may affect the quality of the image, so the method of adding a protective screen can be used to reduce the impact of ambient light. The illumination system can be divided into back illumination, forward illumination, structured light and stroboscopic light according to its illumination method. Among them, the backlighting is that the measured object is placed between the light source and the camera. Its advantage is that it can obtain high contrast image. Forward illumination is that the light source and camera are located on the same side of the measured object, which is easy to install. Structural illumination is to project gratings or linear light sources onto the object under test, and demodulate the three-dimensional information of the object under test according to their distortion. The stroboscopic illumination is to illuminate the object with high frequency light pulses. The camera needs to synchronize with the light source.

Camera lens

FOV (Field of Vision) = required resolution * sub-pixel * camera size / PRTM (part measurement tolerance ratio) lens selection should pay attention to: (1) focal length (2) target height (3) image height (4) magnification factor (5) distance from image to target (5) center point / node (9) distortion

camera

According to different standards, it can be divided into standard resolution digital camera and analog camera. Different cameras and high resolution cameras should be selected according to different practical applications: line scan CCD and area array CCD; monochrome camera and color camera.

Image Acquisition Card

Image acquisition card is only a part of the complete machine vision system, but it plays a very important role. Image acquisition card directly determines the camera interface: black and white, color, analog, digital and so on.

Typically, PCI or AGP compatible capture cards can transfer images to computer memory for processing. Some acquisition cards have built-in multiplexers. For example, you can connect eight different cameras and tell the acquisition card which camera captured the information. Some acquisition cards have built-in digital input to trigger the acquisition card to capture, and the digital output port triggers the gate when the acquisition card captures the image.

Visual Processor

The visual processor integrates the acquisition card and the processor. In the past, when computers were slow, visual processors were used to speed up visual processing tasks. Nowadays, because the acquisition card can transmit image to memory quickly, and the computer is much faster, so the visual processor is less used now.

application area

The main applications of machine vision are detection and robot vision.

For more information, please read the Chinese version.