Resumo

TOSCANO, Iker et al. Automated analysis of SEM micrographs using deep learning. RISTI [online]. 2023, n.49, pp.100-114.  Epub 31-Mar-2023. ISSN 1646-9895.  https://doi.org/10.17013/risti.49.100-114.

The scanning electron microscope (SEM) is commonly used to analyze nanoparticles of different materials and improve manufacturing methods, purification systems, and improve the medical industry, among others. In this article, a systematic mapping of the literature regarding the use of deep learning (AP) techniques for the detection and classification of nanoparticles contained in SEM micrographs is presented. The results reflect those variants of convolutional neural networks (CNN) that are the most widely used techniques to analyze micrographs, obtaining high precision in the projects carried out in the reviewed publications. As proof of concept, examples of the use of the most common approaches in SEM micrographs of CaCO3, including tools like OpenAI, are presented. The results reveal advantages and challenges that arise when using deep learning techniques in the analysis of SEM micrographs.

Palavras-chave : deep learning; SEM micrographs; CaCO₃; nanoparticles; convolutional neural networks.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )