Learning-Based THz Multi-Layer Imaging With Model-Based Masks

This paper demonstrates a learning-based THz multi-layer pixel identification for non-destructive inspection. Specifically, we introduce a recurrent neural network that sequentially learns features from THz spectrogram segments with masks from model-based sparse deconvolution. Initial performance ev...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, P., Koike-Akino, T., Boufounos, P., Tsujita, W., Yamashita, G., Fukuta, T., Nakajima, M.
Format: Conference Proceeding
Language:English
Subjects:
Deconvolution
Image segmentation
Imaging
Inspection
Performance evaluation
Recurrent neural networks
Surface waves
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper demonstrates a learning-based THz multi-layer pixel identification for non-destructive inspection. Specifically, we introduce a recurrent neural network that sequentially learns features from THz spectrogram segments with masks from model-based sparse deconvolution. Initial performance evaluation on a three-layer sample with contents on all surfaces confirms the effectiveness of the proposed method.
ISSN:2162-2035
DOI:10.1109/IRMMW-THz57677.2023.10299043