About | HeinOnline Law Journal Library | HeinOnline Law Journal Library | HeinOnline

LOG IN
LOG IN


17 J. Transp. Sec. 1 (2023-2024)

handle is hein.journals/jtransps17 and id is 1 raw text is: Journal of Transportation Security (2024) 17:1 https://doi.org/1 0.1007/si12198-023-00270-4 BRIEF REPORT Enhancing baggage inspection through computer vision analysis of x-ray images Wisarut Sarail - Napasakon Monbut' • Natchapat Youngchoay'- Nithida Phookriangkrail -Thunpitcha Sattabun'- Thitirat Siriborvornratanakull Received: 10 July 2023 /Accepted: 28 November 2023 © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023 Abstract This research work explores the utility of deep learning algorithms in enhancing the accuracy of weapon detection, specifically guns, within x-ray images of travel bags. Utilizing Faster R-CNN as a baseline model, the research aims to augment detec- tion metrics including accuracy, precision, and recall, thereby fortifying security screening procedures. A comparative study was executed between the Faster R-CNN model and a hybrid model that integrated the Segment Anything (SAM) algorithm with Faster R-CNN. Evidently, the hybrid model displayed an edge in performance with the highest accuracy rate of 86.34%, a marked increase from the 72.02% accu- racy of Faster R-CNN alone. The fusion model demonstrated superior precision, signaling a decrease in false positive instances, although it faced a higher rate of false negatives, as revealed by its recall rate. This study also unearths data limita- tions that could potentially be inhibiting maximum model performance, given the discrepancy between available training data and the sheer volume of the comprehen- sive SJXray dataset. The research concludes by charting avenues for future investi- gation which include data augmentation, SAM model pre-training, and expansion of detection capabilities to encompass a broader array of weapons. This body of work establishes a framework for advancing security measures through the application of artificial intelligence. Keywords Computer vision - X-ray - Weapon detection - Object detection - Self- supervised segmentation Introduction The growth of borderless travel in recent years (UNWTO 2023) has resulted in an increased prevalence of individuals carrying bags and luggage. While personal belongings are generally permitted, the need for luggage inspection in public areas Extended author information available on the last page of the article Published online: 15 December 2023 _ Springer