We report on the performance improvement in Automatic Threat Recognition (ATR) algorithm through the incorporation of self-tuning spectral clustering and a convolutional neural network texture model (CNN). The self-tuning clustering algorithm shows the ability to vastly reduce the amount of bleedout in threat objects resulting in better segmentation and classification. The CNN texture model shows improved detection and classification of textured threats. These additions have markedly improved the ATR. The tests performed using actual CT data of passenger bags show excellent performance characteristics.

© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Samuel M. Song, Namho Kim, Jongkyu Lee, Matthew Wood, Simon Bedford, and Douglas P. Boyd, "Adaptation of self-tuning spectral clustering and CNN texture model for detection of threats in volumetric CT images," Proc. SPIE 10999, Anomaly Detection and Imaging with X-Rays (ADIX) IV, 109990A (Presented at SPIE Defense + Commercial Sensing: April 15, 2019; Published: 14 May 2019); https://doi.org/10.1117/12.2520015.