Loss function for ambiguous boundaries for deep neural network (DNN) for image segmentation

This study deals with the task of segmentation of SEM images of fine ceramics sintered bodies by using deep neural network (DNN). In particular, we focus on misclassification caused by the blurriness of grain boundaries(boundaries between particles). Therefore, we utilize the frequency distribution...

Full description

Saved in:
Bibliographic Details
Published in:Electronics and communications in Japan 2023-12, Vol.106 (4), p.n/a
Main Authors: Hakumura, Yuma, Ito, Taiyo, Matsui, Shiori, Akiba, Yuya, Aoki, Kimiya, Nakashima, Yuki, Hirao, Kiyoshi, Fukushima, Manabu
Format: Article
Language:English
Subjects:
Artificial neural networks
blurriness of grain boundaries
deep neural network
fine ceramics
Frequency distribution
Grain boundaries
Image segmentation
loss function
segmentation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study deals with the task of segmentation of SEM images of fine ceramics sintered bodies by using deep neural network (DNN). In particular, we focus on misclassification caused by the blurriness of grain boundaries(boundaries between particles). Therefore, we utilize the frequency distribution of brightness gradient of grain boundaries and give higher weights to pixels with lower gradient values. Experiments confirmed that the model trained with proposed loss function gave the best prediction results.
ISSN:1942-9533
1942-9541
DOI:10.1002/ecj.12429