Machine Learning for Inline Surface Inspection Systems: Challenges, Approaches, and Application Example

Using deep learning in complex online surface inspection systems is challenging due to different framework conditions. First, time restrictions in production are usually fixed in terms of clock rate and response time. Furthermore, these methods need a lot of data, while typically, the data situation is thin in the beginning as well as continuously unbalanced: defects occur rarely, thereby providing few example data for learning, while the desired detection rate is 100%. Another important issue is that although defect catalogs exist, they often change, especially when automatic inspection is applied for the first time. This is due to imaging systems usually being able to detect more defects than visual-manual inspection, therefore production, management, and quality assurance usually reiterate their prior defect catalogs. However, data-driven methods depend heavily on consistent annotation. Therefore, respective parties must be made aware of this issue on the one hand; on the other hand, annotation and reannotation must be easy and useable by non-experts. Related is the issue of parametrization and traceability. Both are not inherent to neural networks but must be provided to some level to help build trust in machine learning methods. In this chapter, we present a quality inspection system that uses deep neural networks for defect detection under real production conditions in wood manufacturing. We will address how we systematically deal with the above issues both in terms of process and algorithm.