Illicit object detection in X-ray images using Vision Transformers

arXiv:2403.19043v1 Announce Type: new
Abstract: Illicit object detection is a critical task performed at various high-security locations, including airports, train stations, subways, and ports. The continuous and tedious work of examining thousands of X-ray images per hour can be mentally taxing. Thus, Deep Neural Networks (DNNs) can be used to automate the X-ray image analysis process, improve efficiency and alleviate the security officers' inspection burden. The neural architectures typically utilized in relevant literature are Convolutional Neural Networks (CNNs), with Vision …

abstract arxiv automate continuous cs.cv detection hour images locations networks neural networks object per ray security train transformers type vision vision transformers work x-ray