Capsule Attention Based Detection of Contraband in X-Ray Images

Journal Title: Engineering and Technology Journal - Year 2024, Vol 9, Issue 05

Abstract

Aiming at the problem of low detection accuracy caused by the different postures, different sizes, complex backgrounds and overlapping occlusions of contraband in the security checking process, a Matrix capsule network based on attention mechanism (MCAM) is designed by introducing attention mechanism into the capsule network. Firstly, a multi-feature-extraction (MFE) module is designed to solve the difficulty of detecting contraband with different sizes and complex backgrounds; then the Conv2d with Attention for ConvCap (CACC) is constructed in the convolutional layer of the capsule, and the weight information is computed in the channel dimensions of the feature map to give the contraband regions higher coefficients to enhance the contraband detection ability when the poses are different and the occlusion is severe; finally, a new capsule detection layer is designed by utilizing the pose matrix of the capsule to give full play to the detection ability of the matrix capsule network. The mAPs of the proposed model on SIXray, SIXray10, and SIXray100 are 85.10%, 64.05%, and 53.67%, respectively, which are 42.79%, 19.73%, and 9.41% higher than those of the original network, higher than those of the current mainstream detection networks, and the number of parameters of the network and the amount of computation are also lower.

Authors and Affiliations

YAN Zhiming, LI Xinwei, YANG Yi,

Keywords

Related Articles

FAULT TOLERANT ALGORITHM TO COPE WITH TOPOLOGY CHANGES DUE TO POSTURAL MOBILITY

The research involving in providing healthcare services to remote patients have led to the exploration of new solutions to provide effective Quality of Service (QoS) and fault tolerant network for Wireless Body Area Netw...

Design Analysis and Analysis of Roof Structure Work in the Implementation of the Exit Gate and Cafeteria Construction Project at Delta Surya Sidoarjo Hospital

Building design and planning requires a very high level of precision and a relatively long time. Therefore, most consultants and construction implementers (contractors) rely on technical application support during projec...

Literature Study: Internet of Things (IoT) as a Transformative Technology in Building a Smart City Concept

The Internet of Things (IoT) has become one of the most transformative technologies in building the smart city concept. With the potential to connect diverse devices through internet networks, IoT enables increased effic...

The Temperature-Dependent XAFS Debye-Waller Factor of Molybdenum Metal Calculated using Anharmonic Correlated Einstein Model

Temperature-dependent X-ray absorption fine structure (XAFS) Debye-Waller (DW) factor of molybdenum (Mo) metal has been studied under the influence of thermal disorders. This factor is calculated in simple and explicit f...

Utilization of Public Space in Market Area Wamanggu Case Study Merauke

An urban area grows along with the development of community demands as actors in activities. This means that physically and functionally, the intensity and quality of city activities are always changing. The function of...

Download PDF file
  • EP ID EP734689
  • DOI 10.47191/etj/v9i05.01
  • Views 64
  • Downloads 0

How To Cite

YAN Zhiming, LI Xinwei, YANG Yi, (2024). Capsule Attention Based Detection of Contraband in X-Ray Images. Engineering and Technology Journal, 9(05), -. https://europub.co.uk/articles/-A-734689