Balanced affinity loss for highly imbalanced baggage threat contour-driven instance segmentation

Abstract

Autonomous detection of threat items from baggage X-ray imagery is one of the most vital and challenging tasks. Manual detection of these items is a cumbersome, slow, and error-ridden process which is also limited by the examination capacity of the security inspector. To overcome these limitations, many researchers have proposed deep learning-driven approaches to recognize suspicious objects from the baggage X-ray scans. However, threat items are rarely seen in the real world compared to innocuous baggage content. Therefore, when trained with imbalanced data, the performance of the conventional threat detection models drastically decreases. This paper addresses these issues with a contour-driven instance segmentation model optimized with a novel combined loss function, dubbed balanced affinity loss function. In addition to mitigating the class imbalance, this function best handles the fine-grained classification aspect inferred by contours and the instance segmentation. We validated the proposed system on three public baggage X-ray datasets, where it outperformed state-of-the-art methods by 7.76%, 25.81%, and 8.78% in terms of intersection-over-union score. Keywords: Image segmentation, Manuals, Data models, Security, Task analysis, X-ray imaging