On the Impact of Object and Sub-component Level Segmentation Strategies for Supervised Anomaly Detection within X-ray Security Imagery
This addresses the need for improved security screening in transportation by offering an incremental improvement in anomaly detection accuracy for complex electronic items.
The paper tackles the problem of automated anomaly detection in X-ray security imagery by comparing object-level and sub-component-level segmentation strategies, finding that sub-component segmentation yields slightly better performance with ~98% true positive and ~3% false positive rates.
X-ray security screening is in widespread use to maintain transportation security against a wide range of potential threat profiles. Of particular interest is the recent focus on the use of automated screening approaches, including the potential anomaly detection as a methodology for concealment detection within complex electronic items. Here we address this problem considering varying segmentation strategies to enable the use of both object level and sub-component level anomaly detection via the use of secondary convolutional neural network (CNN) architectures. Relative performance is evaluated over an extensive dataset of exemplar cluttered X-ray imagery, with a focus on consumer electronics items. We find that sub-component level segmentation produces marginally superior performance in the secondary anomaly detection via classification stage, with true positive of ~98% of anomalies, with a ~3% false positive.