Log cross section quality metrics: Assessing the usability of roundwood image data for roundwood tracking

The proof of origin of roundwood is becoming increasingly important. As part of the digitization of the forest-based sector and to combat illegal logging, there is a growing interest in tracking wood logs individually. There are several previous publications on biometric wood log tracking based on log image data. A major problem for wood log tracking is the often poor visibility of discriminative features in log ends, such as the annual ring pattern, which makes it very difficult to track such logs. In this work we propose a method that quantifies the usability of image data for the purpose of roundwood tracking. There are no previous publications on this topic. More specifically, we propose a quality map that assesses the usability of different regions of the log cross section and a global quality metric that assesses the quality of entire images. We will show that the local and global quality metrics reliably assess the quality of log cross section images. Furthermore, we will show that the quality map can be used to improve the results of deep learning based log recognition systems. By combining the image data with the local quality map, the roundwood tracking system gets additional information about the usability of the different regions of the log cross section for roundwood tracking, which leads to improvements in most of the results.