Strip steel surface defect image characteristic extraction method based on local characteristic spatial distance

Abstract

The invention relates to a strip steel surface defect image characteristic extraction method based on the local characteristic spatial distance. According to the technical scheme, the method comprises the steps that as for vector data points Xi of one preprocessed strip steel surface defect image, K neighbor points with the same class as the vector data points Xi of one preprocessed strip steel surface defect image are selected from matrix data X formed by the vector data points of all the preprocessed strip steel surface defect images so as to build manifold local characteristic spaces S(Xi), then a multi-manifold divergence Js is measured through the distance between the manifold local characteristic spaces S(Xi), and on the basis that the manifold local structural is kept unchanged, the multi-manifold divergence is maximized to search for a low-dimension projection matrix A, so that the strip steel surface defect image judgment characteristic extraction is achieved. The classification characteristics of the strip steel surface defect images are extracted by maximizing the multi-manifold divergence Js, and the strip steel surface defect image characteristic extraction method has the advantage of improving the strip steel surface defect image recognition effect.

Description

technical field [0001] The invention belongs to the technical field of strip steel surface defect image feature extraction. In particular, it relates to a strip steel surface defect image feature extraction method based on local feature space distance. Background technique [0002] Strip steel is one of the main product forms of the steel industry. It is an essential raw material for aerospace, automobile and ship manufacturing, etc., and is related to the development of many manufacturing industries. In recent years, the demand for strip steel has been increasing and requires a high surface quality. During the rolling process, due to the continuous casting billet, rolling equipment and rolling process, etc., defects such as cracks, scale, scabs, roll marks, scratches, holes and pits appeared on the surface of the rolled steel plate. , These defects not only affect the appearance of the product, but more importantly, reduce the performance of the product such as corrosion ...

AI Technical Summary

Problems solved by technology

However, due to the wide variety and complex features of strip surface defects, the recognition rate based on these traditional feature extraction methods is not ideal.

Images