Classification of Terahertz Images via Caustic Lens and Transfer Learning Terahertz G r nt lerin Kostik Lens ve Transfer grenmesi Y ntemi Kullanilarak Siniflandirilmasi

Arik D. T., ŞAHİN A. B., ERSOY Ö.

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024, Malatya, Turkey, 21 - 22 September 2024, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/idap64064.2024.10711083
  • City: Malatya
  • Country: Turkey
  • Keywords: Caustic Lens, Terahertz Imaging, Transfer Learning
  • Ankara Yıldırım Beyazıt University Affiliated: Yes

Abstract

Our study proposes a novel approach to reduce data processing time and improve classification accuracy in terahertz imaging. By combining a caustic lens with transfer learning, this approach enables faster and more accurate analysis of data obtained from terahertz images. Notably, the method achieved a classification accuracy of 99.38 % for five different letter shapes, demonstrating its effectiveness. This research presents a new pathway to make terahertz imaging systems faster, more accurate, and more cost-effective.