Loading...

A machine learning approach for material classification in MMW imaging systems based on frequency spectra

Shayei, A ; Sharif University of Technology | 2018

575 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ISCAS.2018.8350916
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2018
  4. Abstract:
  5. In this paper, a new approach toward material detection and classification, based on the spectral analysis of millimeter-wave images, using machine learning technique is proposed. The focus of this paper is to detect concealed dangerous materials. It is shown that by using adequate number of training data captured from different materials of interest, the trained machine could detect concealed dangerous materials with an acceptable accuracy. The training phase is performed with materials of varying thickness, shape, background, covering layers and distance. The training data is collected with laboratory experiments in the frequency range of 27-31 GHz with 51 frequency samples. The results show more than 92 percent accuracy in differentiating various materials based on the true-alarm-rate (TAR) metric. © 2018 IEEE
  6. Keywords:
  7. Spectral analysis ; Artificial intelligence ; Image analysis ; Image reconstruction ; Millimeter waves ; Spectrum analysis ; Laboratory experiments ; Machine learning approaches ; Machine learning techniques ; Material classification ; Material detection ; Millimeter-wave images ; Millimeter-wave imaging ; Varying thickness ; Learning systems
  8. Source: Proceedings - IEEE International Symposium on Circuits and Systems ; Volume 2018-May , 2018 ; 02714310 (ISSN); 9781538648810 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/8350916