Plate and strip steel surface defect detection method based on saliency label information propagation model

Abstract

The invention relates to the technical field of industrial surface defect detection, and provides a plate strip steel surface defect detection method based on a significance label information propagation model. The method comprises the following steps of firstly, acquiring a plate strip steel surface image I; then, extracting a bounding box from the image I, and executing a bounding box selectionstrategy; then, performing super-pixel segmentation on the image I, and extracting a feature vector from each super-pixel; then, constructing a significance label information propagation model, constructing a training set based on a multi-example learning framework to train a classification model based on a KISVM, classifying a test set by using the trained model to obtain a category label matrix,calculating a smooth constraint item and a high-level prior constraint item, and optimizing and solving a diffusion function; and finally, calculating a single-scale saliency map under multiple scales, and obtaining a final defect saliency map through multi-scale fusion. The surface defects of the strip steel can be efficiently, accurately and adaptively detected, a complete defect target can beuniformly highlighted, and a non-significant background area can be effectively inhibited.

Description

technical field [0001] The invention relates to the technical field of industrial surface defect detection, in particular to a method for detecting surface defects of strip steel based on a significant label information propagation model. Background technique [0002] Surface defect detection is a key part of controlling the quality of industrial products, especially for my country's booming steel industry. However, at present, many enterprises still mainly use manual detection technology, which relies heavily on the subjective experience of workers, which is prone to high false detection rate and low efficiency. In recent years, automatic detection models based on visual saliency have received extensive attention due to their high efficiency and high detection accuracy. The visual saliency detection method can simulate the human visual attention mechanism, which can solve the problem of limited processing capacity of the brain, and select important visual information for p...

AI Technical Summary

Problems solved by technology

Although this method is efficient and fast, it is difficult to accurately extract the boundary of the defect target when dealing with complex and changeable surface defect types of strip steel, that is, there is a problem of blurred edges

In addition, most of the current saliency detection methods still cannot completely detect the defect target, that is, there is information loss, which shows that these methods cannot effectively identify the characteristics of the defect target, so the detection effect needs to be further improved

[0004] It can be seen that in the existing surface defect detection methods of strip steel, the manual visual inspection method relies heavily on the subjective experience of workers, which is prone to high false detection rate and low efficiency; it is difficult to accurately extract the defect target contour by using the salience detection method of image processing technology Or the edges are blurred, the discrimination of surface defect features is insufficient, and the complete defect target cannot be uniformly highlighted, and the non-significant background area cannot be effectively suppressed

Images