Automated Detection of Threat Materials in X-Ray Baggage Inspection Systems (XBISs)

Manual inspection of baggage X-ray images for the detection of threat materials such as explosives is a tedious and stressful task. We have presented a convolutional neural network (CNN)-based approach for automated detection of threat materials in X-ray images. A deep convolutional generative adversarial network (DCGAN)-based data synthesized model is used for the generation of datasets containing gray images (DXBD1) and pseudo-colored images (DXBD2). A deep CNN-based model, named dual X-ray Baggage (DXB), is proposed for automated classification of threat materials in baggage X-ray images. The proposed model consists of seven layers comprising two convolution layers and five fully connected layers. With this model, accuracies of 98% for gray images with F1 score of 0.97 and 99% for pseudo-colored images with F1 score of 0.99 have been achieved. The proposed model requires the classification time of about 12 s and 6 s, respectively, for gray and pseudo-colored images indicating its suitability for real-time monitoring.