Hot-rolled steel plate surface defect image identification method based on neighborhood information estimation

Abstract

The invention discloses a hot-rolled steel plate surface defect image identification method based on neighborhood information estimation, and belongs to the field of mode identification and machine vision. A local binary pattern catachrestic extraction method is introduced into characteristic extraction of steel plate surface defect images. Characteristics extracted by the method have the advantage that characteristics of defects of the same type are concentrated, and the distinguishing degree of different types of defect characteristics is higher. A neighborhood information estimation window is introduced into the local binary pattern catachrestic extraction, so that the noise interference influence on the characteristics can be effectively resisted. The neighborhood information estimation window is introduced into the local binary pattern catachrestic extraction, so that a phenomenon that the defect characteristics are changed by change influence of lighting and materials is effectively avoided.

Description

technical field [0001] The invention belongs to the field of pattern recognition and machine vision, and in particular relates to an image recognition method for hot-rolled steel plate surface defects based on neighborhood information evaluation. Background technique [0002] Hot-rolled steel plate is one of the main products of the steel industry, and its product quality will directly affect the quality and performance of the final product in many cases. With the increasingly fierce market competition, the product quality of steel plates has become one of the key indicators of domestic and foreign steel market competition, and its quality is directly related to the economic benefits, survival and development of steel enterprises. Due to the limitation of production conditions, there will inevitably be different forms and types of defects on the surface of the steel plate, and the size, number and distribution of defects vary greatly. Defects of different natures, such as i...

AI Technical Summary

Problems solved by technology

That is, the characteristics of the same type of defects are too scattered and not concentrated; while there is a clear overlap between the characteristics of different types of defects, and the degree of feature differentiation is not high;

[0005] (2) Due to the influence of lighting and material changes, the defect characteristics will change greatly, and the stability will decrease, resulting in a decrease in the recognition rate;

[0006] (3) Most of the current defect features are susceptible to noise interference, thus reducing the stability of the recognition rate

Images