Detection Method of Periodic Defects on the Surface of Rolled Materials During Calendering

Abstract

The invention discloses a method for detecting a periodic defect of a calendered material surface in a calendering process. The method comprises the following steps: S1, collecting a defect source image of the calendered material surface to be detected; S2, extracting image features of the defect in the defect source image; S3, pre-judging the periodic defect of the defect source image; and S4, matching adjacent suspected periodic defects in the current longitudinal region by adopting an image relevance matching method one by one to determine the periodic defect. The method can be used for quickly and accurately detecting the periodic defect of the calendered material surface, so that the omission ratio and pseudo-flaw false drop rate of periodic defect detection under various environments can be improved. The method is applicable to any material.

Description

technical field [0001] The invention belongs to the technical field of material surface optical detection, in particular to a method for detecting periodic defects on the surface of a rolled material during the rolling process. Background technique [0002] Periodic defects are serious defects caused by previous process failures in the rolling production process, and early identification can reduce the defect generation rate. Surface defect detection and recognition methods based on machine vision have been applied in various fields, such as paper product surface defect image recognition, textile defect recognition, strip steel surface defect recognition, etc. However, there are few detection methods for periodic defects on the surface of materials, and the existing detection methods also have the following problems: [0003] (1) The Chinese patent "Periodic defect detection device and its method" with the patent number ZL200980112171.0 discloses a magnetic field detection ...

AI Technical Summary

Problems solved by technology

The magnetic field detection method has a low detection rate and is only suitable for metal surfaces

[0004] (2) The Chinese patent "Detection Method and Device for Defects in Periodic Texture Image" with the patent number ZL201010205357.5 discloses a detection method based on machine vision. Periodic defects are misjudged as periodic defects; when the color and shape of some periodic defects change, this method will cause missed detection of periodic defects; when periodic defects occur discontinuously, this method will Periodic defects are misidentified as two sets of periodic defects or passthrough

Images