🤖 AI Summary
This work addresses the scarcity of high-quality, pixel-level annotated defect data in industrial quality inspection, which hinders the training of automated detection models. To overcome this limitation, the authors propose a transferable, parameterized defect modeling approach that constructs three-dimensional geometric defect models based on two-dimensional Voronoi tessellation, embeds them into digital twins of castings, and leverages physics-driven Monte Carlo simulation to generate large-scale, realistic, and diverse synthetic defect datasets. The method enables controllable simulation of rare defects while simultaneously providing precise pixel-level ground truth annotations. It is adaptable across multiple non-destructive testing scenarios and significantly enhances the training and validation performance of vision-based surface inspection algorithms.
📝 Abstract
In industry, defect detection is crucial for quality control. Non-destructive testing (NDT) methods are preferred as they do not influence the functionality of the object while inspecting. Automated data evaluation for automated defect detection is a growing field of research. In particular, machine learning approaches show promising results. To provide training data in sufficient amount and quality, synthetic data can be used. Rule-based approaches enable synthetic data generation in a controllable environment. Therefore, a digital twin of the inspected object including synthetic defects is needed. We present parametric methods to model 3d mesh objects of various defect types that can then be added to the object geometry to obtain synthetic defective objects. The models are motivated by common defects in metal casting but can be transferred to other machining procedures that produce similar defect shapes. Synthetic data resembling the real inspection data can then be created by using a physically based Monte Carlo simulation of the respective testing method. Using our defect models, a variable and arbitrarily large synthetic data set can be generated with the possibility to include rarely occurring defects in sufficient quantity. Pixel-perfect annotation can be created in parallel. As an example, we will use visual surface inspection, but the procedure can be applied in combination with simulations for any other NDT method.