Journal of Physics Conference Series · 2018 · 124 citations · 25 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine LearningDeep LearningDefect ClassificationImage ClassificationIndustrial InspectionObject DetectionPattern RecognitionDeep Learning-based ClassificationImage-based Defect ClassificationSliding Window AlgorithmsWeld Defect DetectionWeld DefectsWeld Joint DetectionWelded JointsWelding Inspection
In this paper, we propose an automatic detection schema including three stages for weld defects in x-ray images. Firstly, the preprocessing procedure for the image is implemented to locate the weld region; Then a classification model which is trained and tested by the patches cropped from x-ray images is constructed based on deep neural network. And this model can learn the intrinsic feature of images without extra calculation; Finally, the sliding-window approach is utilized to detect the whole images based on the trained model. In order to evaluate the performance of the model, we carry out several experiments. The results demonstrate that the classification model we proposed is effective in the detection of welded joints quality.
25
Ehsan Hosseini-Asl, Jacek M. Żurada, Olfa Nasraoui · IEEE Transactions on Neural Networks and Learning Systems · 2015 · 216 citations · Full text