[8a-A23-1~12] CS.2 Code-sharing session of 3.2&4.4

11:30 AM - 11:45 AM JST(2:30 AM - 2:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[8a-A23-10] Enhancing Image Quality in Single-Pixel Imaging Using Non-negative Matrix Factorization and Deep Learning

〇(M2)Kenya Sugimoto¹, Fan Wang¹, Tomoyoshi Ito¹, Tomoyoshi Shimobaba¹ (1.Chiba Univ.)

Keywords:

single-pixel imaging,non-negative matrix factorization,deep learning

This paper proposes a high-quality single-pixel imaging method combining non-negative matrix factorization (NMF) and deep learning. We developed a deep learning-based reconstruction decoder optimized for NMF patterns. Experimental results successfully demonstrate that our proposed approach significantly enhances reconstructed image quality at an ultra-low sampling rate of only 0.39%.