Segmentation of backscattered electron images of geopolymers using convolutional autoencoder network

作者：

Highlights：

• An automatic CNN-based model is presented for multi-phase segmentation of BSE images.

• The proposed model compares with conventional segmentation methods.

• Result shows the self-learning capability of CNN model on poorly annotated area.

• The model performs magnification independent.

摘要

•An automatic CNN-based model is presented for multi-phase segmentation of BSE images.•The proposed model compares with conventional segmentation methods.•Result shows the self-learning capability of CNN model on poorly annotated area.•The model performs magnification independent.

论文关键词：Geopolymer,Backscattered electron imaging,Segmentation,Deep learning,Convolutional neural networks

论文评审过程：Received 10 October 2021, Revised 20 May 2022, Accepted 9 June 2022, Available online 11 June 2022, Version of Record 22 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117846