Defect inspection is one of the most critical tasks in the industry as it can reduce risks of production stops and assure quality control. In recent years, multiple industries have been adopting computer vision systems, especially based on deep learning techniques, as their main detection methods to improve efficiency, reduce risks and human resources, and enhance real-time performance. However, its adoption in the industry is still limited by the labor-intense and time-consuming process of collecting high-quality custom training datasets. At the same time, many industries have access to the CAD models of the components they want to detect or classify as part of the design process. Taking this into account, in the present work, we analyze the performance of various image classification models to visually detect defects in production. Our method systematically generates synthetic datasets from CAD models using Blender to train neural networks under different settings. The proposed method shows that image classification models benefit from a diversity of the range of defect values during training but struggle to identify low-resolution defects, even for state-of-the-art architectures like Vision Transformer and ConvNext or SqueezeNet, which proved to have comparable performance to these networks. Similarly, adding background, texture, and camera pose to training examples provides more contextual information to image classification models but does not necessarily help them detect the defects accurately. Finally, we observed that using a unique tolerance value for all flange pipe sizes can negatively impact the detection accuracy because, for larger pipe flanges, minor defects are not as perceptible as for small flanges.
|Date made available
|KAUST Research Repository