A board defect area extraction method and device

Abstract

The invention belongs to the technical field of industrial detection, and discloses a board defect area extraction method and device, and the method comprises the steps of obtaining a to-be-detected board image, and carrying out the segmentation of the image, and obtaining a plurality of detection units; obtaining gray threshold values in one-to-one correspondence with the multiple detection units; and calculating a gray average value of the detection unit, comparing the gray average value with a corresponding gray threshold value, and judging whether the detection unit contains defects or not. According to the invention, the to-be-detected board image is divided into the plurality of detection units, whether each detection unit contains defects or not is judged, the accuracy of the judgment result is improved, meanwhile, all the detection units containing the defects jointly form the defect area on the board; when the defects are further identified subsequently, only the detection units containing the defects are analyzed, so that the amount of data needing to be processed is greatly reduced, and the time required for detecting the defects of the board is shortened.

Description

Technical field[0001]The present invention belongs to the field of industrial detection, and in particular, to a method and apparatus for extracting a plate defect region.Background technique[0002]Whether the plate surface of the sheet is defective is one of the standards that measures the quality of the sheet, generally detecting the panel defect detection directly on the production line to determine whether the produced sheet is qualified. Taking a particleboard as an example, the most advanced particle production equipment is currently a continuous press production line. Machine vision technology is the mainstream of industrial non-destructive testing technology, but in the field of plate surface defect detection, lack of relatively mature systems to achieve machine visual techniques. Therefore, most of the particleboard manufacturers still rely on workers to detect with naked eye on continuous production lines, and determine whether produced particleboard panels have defects. Ho...

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