Learning-Based Image Synthesis for Hazardous Object Detection in X-Ray Security Applications

Hyo Young Kim, Sung Jin Cho, Seung Jin Baek, Seung Won Jung, Sung Jea Ko

Research output: Contribution to journalArticlepeer-review

Abstract

X-ray baggage inspection has been widely used for maintaining airport and transportation security. Towards automated inspection, recent deep learning-based methods have attempted to detect hazardous objects directly from X-ray images. Since it is challenging to collect a large number of training images from real-world environments, most previous learning-based methods rely on image synthesis for training data generation. However, these methods randomly combine foreground and background images, restricting the effectiveness of synthetic images for object detection. To solve this problem, in this paper, we propose a learning-based X-ray image synthesis method for object detection. Specifically, for each foreground object to be synthesized, we first estimate positions difficult to detect by the object detector. These positions and their corresponding confidence values are then used to construct a difficulty map, which is used for sampling the target foreground position for image synthesis. The performance analysis using various state-of-the-art object detectors shows that the proposed synthesis method can produce more useful training data compared with the conventional random synthesis method.

Original languageEnglish
Pages (from-to)135256-135265
Number of pages10
JournalIEEE Access
Volume9
DOIs
Publication statusPublished - 2021

Keywords

  • Deep learning
  • X-ray
  • inspection
  • neural network
  • object detection

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint

Dive into the research topics of 'Learning-Based Image Synthesis for Hazardous Object Detection in X-Ray Security Applications'. Together they form a unique fingerprint.

Cite this