Product surface scratch detecting method based on machine vision

Abstract

The invention discloses a product surface scratch detecting method based on machine vision, and relates to the technical field of machine vision defect detection. The product surface scratch detectingmethod specifically comprises the steps that signals are received, and image information is collected; texture inhibition is conducted on images through a convolutional neural network, nonclassical feeling wild inhibition is conducted on the collected images first, then the inhibited images are input into the trained convolutional neural network to be subjected to texture estimation, and at lastthe images are subjected to dynamic iteration inhibition to initially obtain scratch images; lagged double-threshold scratch connection is conducted, breakage scratches in a small range are connected,a high threshold and a low threshold are adopted to conduct binaryzation on the images, and the edges of the images are connected with the high threshold as the basis and the low threshold as the compensation; and the scratch images are thinned. According to the product surface scratch detecting method, mobile phone partition images are quickly collected in real time and are subjected to a seriesof treatment, so that surface scratches are efficiently and accurately detected, and detecting results are displayed in real time.

Description

technical field [0001] The invention relates to the technical field of machine vision defect detection, in particular to a machine vision-based product surface scratch detection method. Background technique [0002] Product surface scratch detection is an indispensable detection content in defect detection. Due to the influence of materials and processes, scratches are sometimes formed on the surface of the product during the production process, and the scratches have various shapes, coupled with background texture interference, which increases the difficulty of manual detection of scratches. With the continuous improvement of the market's requirements for product quality and product appearance, manufacturers have higher and higher requirements for scratch detection. Faced with this high-precision detection requirement, manual detection due to its high cost, low efficiency, and error The reason for the high rate has become no longer applicable. Therefore, machine vision in...

AI Technical Summary

Problems solved by technology

Due to the influence of materials and processes, scratches are sometimes formed on the surface of the product during the production process, and the scratches have various shapes, coupled with background texture interference, which increases the difficulty of manual detection of scratches

With the continuous improvement of the market's requirements for product quality and product appearance, manufacturers have higher and higher requirements for scratch detection. Faced with this high-precision detection requirement, manual detection due to its high cost, low efficiency, and error The reason for the high rate has become inapplicable

Images