Photoelectric Sensors

Laser
Sensors

Pressure Sensors

Safety
Curtain

Displacement Sensors



Machine Vision

	Machine Vision Systems
	Machine Vision Systems Overview
	Image Processing Principles
	Inspection Functions

Machine Vision Functions

	Area Judgment by Binarization
	Position Detection
	Dimension Measurement
	Additional Image Functions


	Lighting Techniques
	Information About Lenses
	Image Processing Techniques
	Examples of Technique Application

Keyence Product Information Site

	Vision Systems

Image Processing Principles

Pattern matching

Recognizes the pattern of an image

The target pattern of a reference image is registered and stored in a pattern window. The pattern window then scans the specified search region from the upper lefthand corner to the lower right-hand corner to detect the position that best matches the registered image.

Pattern matching with grayscale processing

Pattern matching uses grayscale image processing, which assigns 256 levels of gray to each pixel and then recognizes the pattern of the target. Binary processing, in contrast, recognizes images only as black and white.

Pattern matching with color extraction

The CV-700/301 Series color vision system recognizes the pattern stored in the pattern window not only through brightness (CV-301), but also through RGB technology which assigns 256 levels of red, green and blue color to each pixel (CV-700). The CV-700/301 Series is ideal for detection of targets with the same shape but different colors.

Sub-pixel processing

Usual image processing is performed in units of 1 pixel, while the sub-pixel processing method performs position detection in units down to 0.001 pixels. This enables high-accuracy position detection, expanding the application range to precise part location and dimension measurement.

Normalized correlation method

Accurate pattern matching without being affected by changes in brightness.

The grayscale pattern matching method recognizes each pixel of a reference image pattern as one of 256 levels of gray, and it compares this data with the information of the image on the screen to detect the position. However, with this method accurate position detection is sometimes difficult because the absolute value of the gray scale data is easily affected by variations in ambient light.

The normalized correlation method allows for stable pattern matching without being affected by ambient light. As the following pictures show, the average brightness of the whole image is subtracted from the brightness (grayscale data) of each pixel for both the reference image and input image. This is called normalization, which eliminates the difference in the brightness of both whole images. Then, the image is located at the position where the patterns of the reference and input images best match (i.e. highest correlation), and the position of the target pattern in the image is accurately detected.

Edge detection

By setting the edge detection window on the image screen, you can locate the section where the brightness changes within the image and recognize it as an edge. This method is effective for detecting the absolute coordinate of an edge or for dimensional inspection of workpieces.

Basic Principle of Edge Detection

The edge is the border which separates a bright area from a dark area within an image. Detecting an edge means detecting this border of different shades through image processing. Edges can be obtained through the following process.

Perform Projection Processing

Perform projection processing on the image within the measurement area. Projection processing scans the image vertically to the detection direction in order to obtain the average intensity of each projection line. The waveform of each projection line is called the projection waveform.

What is Projection Processing?

Projection processing is used to obtain the average intensity of the projection direction,
and it minimizes false detection caused by noise within the measurement area.

Perform Differential Processing

Differential processing is performed based on the projection waveform, and larger deviation values are obtained when the difference in shades which form edges is distinct.

What is Differential Processing?

Variation in shade (intensity) is obtained by this process and all influences caused by changes in absolute intensity values within the measurement area are eliminated.

(Example) The absolute intensity value is "0" if there are no changes in shade. If color changes from white (255) to black (0), the variation is -255.

Maximum Deviation Value Always Needs to be 100%

In order to minimize external effects such as changes in illumination intensity, etc., necessary compensation needs to be performed so that the maximum deviation value is always maintained at 100%.
Then, the edge position is determined from the peak point of the differential waveform which exceeds the preset "edge sensitivity (%).
Because the peak point of changes in shade is detected, reliable edge detection is realized even for actual production lines where illumination intensity frequently changes.

	Page Top

Copyright(c) 2007 KEYENCE CORPORATION. All rights reserved.	\| Privacy \| Terms of Use \| Contact \| Produced by