Visual detection method and device for nameplate surface scratch defects

Abstract

The invention provides a visual detection method and device for a nameplate surface scratch defect. The visual detection method comprises the following steps: acquiring an original image; performing logarithmic equilibrium transformation on the original image; carrying out binarization processing on the image after logarithmic equilibrium transformation by adopting an automatic threshold segmentation algorithm; determining a connected domain Smax with the largest area in all connected domains of the image after binarization processing, and performing open operation on the connected domain Smax by using a circular structure element with a set radius to obtain a rectangular region; cutting the surface image of the to-be-detected nameplate from the original image by adopting the rectangular area; preprocessing the surface image of the to-be-detected nameplate; and segmenting a scratch defect area from the preprocessed image by adopting a dynamic threshold segmentation algorithm. The gray level transformation curve can be well adjusted, the contrast in a specific range is highlighted, and the to-be-detected nameplate image can be extracted from the original image in the subsequent step; the accuracy of identifying the scratch defect area can be improved; the method can be suitable for various scenes with different nameplates.

Description

technical field [0001] The invention relates to the technical field of industrial manufacturing, in particular to a visual detection method and device for scratch defects on the surface of a nameplate. Background technique [0002] At present, the commonly used nameplate surface defect detection algorithm first needs to create a template for the sample, and then uses the template matching method combined with the background difference to extract defect information. However, the template matching method first needs to create a template of qualified samples, which is not suitable for those scenarios where the content of the nameplate is constantly changing. The reason is that it is impossible to create a template for each nameplate in the industrial production process. Manually. Moreover, the template matching method requires high precision, and the nameplate to be tested needs to be completely aligned with the sample nameplate. However, scratch defects are usually in the sha...

AI Technical Summary

Problems solved by technology

However, the template matching method first needs to create a template of qualified samples, which is not suitable for those scenarios where the content of the nameplate is constantly changing. The reason is that it is impossible to create a template for each nameplate in the industrial production process. Manual

Moreover, the template matching method has high requirements on accuracy, and the nameplate to be tested needs to be completely aligned with the sample nameplate. However, scratch defects are usually in the shape of some lines. If the matching accuracy is slightly poor, it will cause a large number of false detections.

Images