Oil pipeline weld defect detection method based on X-ray image

Abstract

The invention discloses an oil pipeline weld defect detection method based on an X-ray image. A single-channel weld grayscale image is processed through saliency transformation to get a saliency image. The invention proposes a fast visual saliency (FVS) algorithm which is used to get a saliency image. The original image and the saliency image constitute a two-channel input. Then, a training sample is extracted through a sliding window, and LBPs (Local Binary Patterns) and grayscale co-occurrence features are extracted and taken as a feature vector together with an image column vector. The invention proposes a feature extraction method based on discriminant sparse reconstruction projections (DSRP), which makes the algorithm more robust while reducing the dimension of feature data. Finally, classification is carried out by training a SVM (Support Vector Machine) classifier, thus improving the accuracy of detection.

Description

Technical field: [0001] The invention is used in the field of pipeline welding defect detection, and particularly relates to the field of X-ray weld image defect detection. Background technique: [0002] X-ray image defect detection is a prerequisite step for defect recognition, and the result of defect detection will affect whether the recognition is correct. The defect detection of X-ray images has the following difficulties: the background of the weld has large fluctuations, the edge of the defect is blurred, the existence of welding waves makes the background of the weld more complex and changeable, and many noises interfere with the defect. Traditional segmentation algorithms cannot simultaneously overcome the above-mentioned difficulties and obtain good detection results. The results obtained by the segmentation algorithm will contain some noise, solder waves and some false defects. Usually, some detected small area targets can be removed by morphological processing,...

AI Technical Summary

Problems solved by technology

The defect detection of X-ray images has the following difficulties: the background of the weld has large fluctuations, the edge of the defect is blurred, the existence of welding waves makes the background of the weld more complex and changeable, and many noises interfere with the defect

Traditional segmentation algorithms cannot overcome the above-mentioned difficulties at the same time and obtain good detection results.

The results obtained by the segmentation algorithm will contain some noise and noise, solder waves and some false defects

Usually, some detected small area targets can be removed by morphological processing, but solder waves and false defects cannot be separated from defects

[0003] Now people have used the method of pattern recognition for defect detection, and the method of extracting features to train classifiers to classify defects and non-defects, so as to solve the problem that traditional segmentation algorithms cannot separate solder waves, pseudo defects and defects

However, the method of classifying segmented images relies too much on the segmentation results, and the usual segmentation algorithms do not have a unified evaluation standard, so there is no mature X-ray optimal segmentation algorithm

Images