On-line detection method of small defect on metal plate strip surface

Abstract

The invention relates to an on-line detection method of small defects on metal plate strip surfaces, which comprises the following steps: separating R, G, B channel images from a color image collected by a camera, wherein the R, G, B channel images respectively correspond to the distribution of reflected light intensities of red, green, and blue light sources, calculating a surface dip angle distribution map of the R channel image and the B channel image according to a designed surface dip angle calculation method, and then detecting small defects on the metal plate strip surface according to the surface dip angle distribution map; the G channel image is a metal plate strip surface image obtained in an illumination mode between bright and dark fields, and routine defects on the metal plate strip surface can be detected through the G channel image by current algorithm. The complete defect information of the metal plate strip surface can be obtained by combining the detection results of small defects and routine defects.

Description

technical field [0001] The invention relates to a method for on-line detection of tiny defects on the surface of metal strips and a device and algorithm for realizing the method. Through the combination of three strip light sources of red, green and blue and a single color linear array CCD camera, the camera can be detected without increasing the number of cameras. In the case of high resolution, the online detection of tiny surface defects can be realized. And while detecting tiny defects, conventional defects can also be detected through existing algorithms, and the complete defect information of the metal strip surface can be obtained by combining the detection results of small defects and conventional defects. Background technique [0002] Surface defects are an important factor affecting the quality of metal strips, especially for high-quality metal strips, such as automotive panels, home appliance panels, stainless steel, etc., the requirements for surface defects are ...

AI Technical Summary

Problems solved by technology

[0005] However, bright field lighting, dark field lighting and methods between bright and dark field lighting are not capable of detecting small defects.

In order to improve the detection ability of small defects, the resolution of the camera needs to be increased, which will increase the cost of the equipment, and the increase of the resolution of the camera will cause an increase in the amount of data, which puts forward higher requirements for the data processing capability of the system

Images