Machine vision typical structure

- Dec 18, 2018-

A typical machine vision system includes the following five blocks:

LLUMINATION Lighting is an important factor that affects the input of the machine vision system, which directly affects the quality and application effect of the input data. due to the absence of a general machine vision lighting device, a corresponding lighting device is selected for each particular application instance to achieve the best effect. The light source can be divided into visible light and non-visible light. Several commonly used visible light sources are incandescent, fluorescent, mercury and sodium. the disadvantage of visible light is that the light can not remain stable. How to keep the light stable to a certain extent is a problem that needs to be solved in the practical process. On the other hand, the ambient light may affect the quality of the image, so that the effect of the ambient light can be reduced using a method of adding a protective screen. The illumination system can be divided into: back illumination, forward illumination, structure light and frequency flash illumination, etc. in which the back illumination is between the light source and the camera, with the advantage of being able to obtain an image of high contrast. The forward illumination is that the light source and the camera are on the same side of the object to be measured, which is convenient for installation. the structure light illumination is to project a grating or a line light source or the like onto the object to be measured, and the three-dimensional information of the object to be measured is demodulated according to the distortion generated by them. The frequency flash illumination is to irradiate a high-frequency light pulse onto an object, and the camera shooting request is synchronized with the light source. 

Machine vision 600


the lens FOV = required resolution * sub-pixel * camera size/ PRTM (part measurement tolerance ratio) The lens selection should be noted: The focus of the target is the target height, the image height and the image to the target's distance, the center point/ node's distortion How to Determine the Focal Length of the Lens in the Visual Inspection The following factors must be taken into account for selecting a suitable industrial lens for a particular application: · Field of view-size of the area to be imaged. · Working distance (WD)-the distance between the camera lens and the observed object or area. The size of the CCD-camera imaging sensor device. machine vision lens machine vision lens These factors must be treated in a consistent manner. If the width of the object is measured, the CCD specifications in the horizontal direction need to be used, and so on. If measured in inches, the measurements are made in feet and then converted to millimeters. Refer to the following example: 1/ 3 ”C-type mounted CCD camera (horizontal 4. 8 mm). The distance from the object to the front of the lens is 12” (305 mm). The field of view or the size of the object is 2.5 ”(64 mm). Conversion factor is 1” = 25. 4 mm (rounded). FL = 4.8 mm x 305 mm/ 64 mm FL = 1464 mm/ 64 mm FL = 23 mm lens requirement FL = 0.19 ”x 12”/ 2.5 "FL = 2.28 ”/ 2.5” FL = 0.912" x 25. 4 mm/ inch FL = 23 mm lens requirement Note: Do not confuse the working distance with the distance of the object to the image. The working distance is the distance from the front of the industrial lens to the object to be observed. and the distance of the object to the image is the distance between the ccd sensor and the object. The working distance must be used when calculating the required industrial lens focal length.

High-speed camera 

According to different standards, it can be divided into standard resolution digital camera and analog camera. 

To select different cameras and high-resolution cameras according to different practical applications: according to the imaging color, the color camera can be divided into a color camera and a black-and-white camera; 

According to the resolution, the number of pixels is of the ordinary type with the pixel number of less than 38 thousand, and the number of pixels is more than 38 thousand high-resolution type; 

The size of the light-sensitive surface can be divided into 1/ 4, 1/ 3, 1/ 2 and 1-inch cameras. 

The scanning mode can be divided into two ways: line scanning camera (line array camera) and surface scanning camera (surface array camera); 

(the surface scanning camera can be divided into interlaced scanning camera and progressive scanning camera); 

It can be divided into the general camera (internal synchronization) and the camera with the external synchronization function. 

Image acquisition card:

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

The comparison is typically a pci or agp-compatible capture card that can be quickly transferred to a computer memory for processing. Some of the acquisition cards have a built-in multi-way switch. For example, you can connect eight different cameras and then tell the acquisition card to take the information captured by that camera. The acquisition card has a 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 set acquisition card is integrated with the processor. in that past, when the speed of the computer is slow, the visual processor is adopt to accelerate the visual processing task. The acquisition card transfers the image to the memory and then calculates the analysis. The current mainstream configuration PLC, and the configuration is high, the visual processor has almost exited the market.