Method and device for extracting defect area on board surface

Abstract

The invention belongs to the technical field of industrial inspection, and discloses a method and a device for extracting a defect area on a board surface. The method for extracting a defect area on a board surface includes: acquiring and dividing an image of the board surface to be detected to obtain a plurality of detection units; Grayscale thresholds corresponding to multiple detection units one-to-one; calculate the grayscale mean of the detection units and compare them with the corresponding grayscale thresholds to determine whether the detection units contain defects. The invention divides the image of the board surface to be detected into a plurality of detection units, and judges whether each detection unit contains a defect, thereby improving the accuracy of the judgment result. When the defect is further identified, only the detection unit containing the defect can be analyzed, which greatly reduces the amount of data that needs to be processed, thereby reducing the time required for defect detection on the board surface.

Description

technical field [0001] The invention belongs to the technical field of industrial inspection, and in particular relates to a method and device for extracting defect areas on a board surface. Background technique [0002] Whether there are defects on the board surface of the board is one of the standards to measure the quality of the board. Generally, the board surface defect detection is carried out directly on the production line to judge whether the produced board is qualified. Taking particleboard as an example, the most advanced particleboard production equipment is the continuous press production line. Machine vision technology is currently the mainstream of industrial non-destructive testing technology, but in the field of plate surface defect detection, there is still a lack of relatively mature systems to realize the application of machine vision technology. Therefore, at present, most particleboard manufacturers still rely on workers to inspect with the naked eye o...

AI Technical Summary

Problems solved by technology

In the existing technology, the size of the image generally collected is about 2560×2048 pixels, the amount of data is large, and the calculation takes a long time, which cannot meet the running speed of the production line

If the calculation speed is increased to adapt to the running speed of the production line, the only way to reduce the amount of calculation is to reduce the detection accuracy, but this may increase the missed detection rate and false detection rate.

Images