Metal surface scratch detection method and device

Abstract

The invention relates to the field of image processing, in particular to a metal surface scratch detection method and device, and the method specifically comprises the steps: obtaining a first image of a to-be-detected surface; performing Fourier transform on the first image to obtain a frequency domain graph; processing the frequency domain graph through a filter, and removing high and low frequency parts in the frequency domain graph; performing inverse Fourier transform on the removed frequency domain image to obtain a second image of the to-be-detected surface; judging whether a standard scratch exists in the second image or not, and displaying a judgment result. The device specifically comprises an acquisition module, a filter module and a judgment module. The acquisition module is composed of a calling sub-module and an image acquisition sub-module, the filter module is composed of a filter parameter setting sub-module, a frequency domain image acquisition and conversion sub-module and a third image acquisition sub-module, and the judgment module is composed of a scratch area detection sub-module, a feature area acquisition sub-module and a standard scratch judgment sub-module.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and device for detecting scratches on metal surfaces. Background technique [0002] In the process of industrial automation, it has become a development trend for machines to replace manpower to complete various tasks in production and manufacturing. How to improve the reliability and efficiency of machine processing has gradually become the focus. For example, for the yaw ring forgings of wind turbines, during the production process, due to the possible adhesion of hard particles on the rollers of the processing equipment, there will be scratches on the surface of the cooled forgings, and when the scratches are severe enough , there will be some potential safety hazards and assembly errors; in order to avoid such problems, defect detection is carried out on the surface of the cooled forging to determine whether it is qualified. [0003] In the process of realizing the p...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventors found the following problems in the existing technology: On the one hand, using manual detection method, due to the large number of products, the cost of labor is too high, and at the same time, long-term work of manpower is prone to fatigue, and it is easy to appear Misjudgment; on the other hand, for small scratches that are difficult to distinguish with the naked eye, manual inspection may not be able to find them in time, so the efficiency in the inspection process is very low, which will inevitably cause waste of manpower and material resources, and in the traditional In the current scratch detection method, its detection efficiency is low so that it cannot meet the requirements of industrial scratch defect detection

Images