@inproceedings{328c13b4315d43c78e5da99a1b865cfd,
title = "Tobacco Impurities Detection with Deep Image Segmentation Method on Hyperspectral Imaging",
abstract = "The detection of impurities in tobacco raw materials is an important task, and the performance of detection algorithms directly affects the quality of tobacco products. The hyperspectral imaging system simultaneously captures the visible and near-infrared spectra containing rich spectral information that can accurately reflect material categories. In this paper, we propose a novel deep learning-based tobacco impurities detection method on hyperspectral data. It is a U-net like structure that progressively extracts multi-scale discriminant features and fuses them to find the impurities in the scene. Experiments conducted on the collected dataset show that the proposed segmentation model yields superior performance compared to other detection methods.",
keywords = "deep learning, hyperspectral image processing, Image segmentation, impurities detection",
author = "Linruize Tang and Min Zhao and Shuaikai Shi and Jie Chen and Jinwei Li and Qiang Li and Rengang Li",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023 ; Conference date: 14-11-2023 Through 17-11-2023",
year = "2023",
doi = "10.1109/ICSPCC59353.2023.10400280",
language = "英语",
series = "Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023",
}