Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search

TL;DR

This paper presents a novel approach combining Bag of Visual Words and Selective Search for handgun detection in X-ray baggage images, achieving high accuracy and pioneering the use of Selective Search in this context.

Contribution

It introduces the first application of Selective Search for localization in baggage X-ray images combined with BoVW for handgun detection, demonstrating promising results.

Findings

Precision of 80% achieved

True positive rate of 92% achieved

First use of Selective Search in baggage X-ray images

Abstract

Baggage inspection systems using X-ray screening are crucial for security. Only 90% of threat objects are recognized from the X-ray system based in human inspection. Manual detection requires high concentration due to the images complexity and the challenges objects points of view. An algorithm based on Bag of Visual Word (BoVW) with Selective Search is proposed in this paper for handguns detection in single energy X-ray images from the public GDXray database. This approach is an adaptation of BoVW for X-ray baggage images context. In order to evaluate the proposed method the algorithm effectiveness recognition was tested on all bounding boxes returned by selective search algorithm in 200 images. The most relevant result is the precision and true positive rate (PPV = 80%, TPR= 92%). This approach achieves good performance for handgun recognition. In addition, it is the first time the Selective Search localization algorithm was tested in baggage X-ray images and showed possibilities with Bag of Visual Words.