SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection
This work addresses the challenge of limited defect diversity in training data for industrial visual inspection systems, though it is incremental as it applies existing synthetic data methods to a specific domain.
The authors tackled the problem of insufficient training data for machine learning in metal surface inspection by developing a complete image synthesis pipeline, which generated synthetic datasets for milled and sandblasted aluminum surfaces and used them to train a defect segmentation model, achieving results comparable to real data.
The use of machine learning (ML) methods for development of robust and flexible visual inspection system has shown promising. However their performance is highly dependent on the amount and diversity of training data. This is often restricted not only due to costs but also due to a wide variety of defects and product surfaces which occur with varying frequency. As such, one can not guarantee that the acquired dataset contains enough defect and product surface occurrences which are needed to develop a robust model. Using parametric synthetic dataset generation, it is possible to avoid these issues. In this work, we introduce a complete pipeline which describes in detail how to approach image synthesis for surface inspection - from first acquisition, to texture and defect modeling, data generation, comparison to real data and finally use of the synthetic data to train a defect segmentation model. The pipeline is in detail evaluated for milled and sandblasted aluminum surfaces. In addition to providing an in-depth view into each step, discussion of chosen methods, and presentation of ML results, we provide a comprehensive dual dataset containing both real and synthetic images.