Deep convolutional neural network image processing method providing improved signal-to-noise ratios in electron holography. (17th March 2021)

• Record Type: Journal Article
• Authors: Asari, Yusuke; Terada, Shohei; Tanigaki, Toshiaki; Takahashi, Yoshio; Shinada, Hiroyuki; Nakajima, Hiroshi; Kanie, Kiyoshi; Murakami, Yasukazu
• Is Part Of: Microscopy. Volume 70:Number 5(2021)
• Page Start: 442
• Page End: 449
• Publication Date: 2021-03-17
• Subjects: electron holography -- image processing -- noise reduction -- machine learning -- convolutional neural network -- nanoparticles; Microscopy -- Periodicals; 502.825
• DOI: 10.1093/jmicro/dfab012
• Languages: English
• ISSNs: 2050-5698

Abstract

Abstract: An image identification method was developed with the aid of a deep convolutional neural network (CNN) and applied to the analysis of inorganic particles using electron holography. Despite significant variation in the shapes of α-Fe2 O3 particles that were observed by transmission electron microscopy, this CNN-based method could be used to identify isolated, spindle-shaped particles that were distinct from other particles that had undergone pairing and/or agglomeration. The averaging of images of these isolated particles provided a significant improvement in the phase analysis precision of the electron holography observations. This method is expected to be helpful in the analysis of weak electromagnetic fields generated by nanoparticles showing only small phase shifts.