Threat Object Detection in X-ray Images Using SSD, R-FCN and Faster R-CNN
2020 International Conference on Computing, Networking, Telecommunications & Engineering Sciences Applications (CoNTESA)
Inspection of baggage for threat objects (such as explosives) using X-ray images is a priority ta... more Inspection of baggage for threat objects (such as explosives) using X-ray images is a priority task for preventing terrorist attacks. Currently, the checking of baggage is based on a semi-automated system that consists of both a human operator and also assisted by image detection. In order to apply effective object detection, accurate object detection models like the: Single Shot Detector, Region-based Fully Convolutional Network (R-FCN) and Faster R-CNN (Region-based Convolutional Neural Network) must be considered. These models are used by applying different techniques of feature extraction, such as: Inception-v2, MobileNet-v2 and ResNet101. In conclusion, the best detection was achieved by the combination of the Faster R-CNN detection models and the ResNet101 feature extractor, achieving an accuracy of 87.58% (±0.75% error margin).
Uploads
Papers by Maaruf Ali