Machine vision-based automatic identification and rating method and system for low-magnification acid etching defect

Abstract

A machine vision-based automatic identification and rating method and system for a low-magnification acid etching defect. The method is used for automatically identifying and rating a defect of a low-magnification aid etching sample of an steel material or a steel billet or a continuous casting billet after acid etching, and comprises: according to a first preset condition, performing image acquisition on the low-magnification acid etching sample of the steel material to obtain a first image (S); performing automatic image processing on the first image to obtain a second image (S); according to a second preset condition, performing image segmentation on the second image to obtain a third image (S); according to a pre-known defect type, performing defect mode identification on the third image to obtain the distribution data of defect modes in the low-magnification acid etching sample (S); obtaining the quantitative data of various defect modes in the low-magnification acid etching sample according to the third image and the distribution data of the defect modes in the low-magnification acid etching sample (S); and performing rating on the defect in the low-magnification acid etching sample according to the quantitative data of the defect modes in the low-magnification acid etching sample (S).