The application of convolutional neural networks for tomographic reconstruction of hyperspectral images

被引：10

作者：

Huang, Wei-Chih ^{[1
,2
]}

Peters, Mads Svanborg ^{[3
,4
]}

Ahlebaek, Mads Juul ^{[1
,2
]}

Frandsen, Mads Toudal ^{[1
,2
]}

Eriksen, Rene Lynge ^{[4
]}

Jorgensen, Bjarke ^{[3
]}

机构：

[1] Univ Southern Denmark, CP3 Origins, Campusvej 55, DK-5230 Odense M, Denmark

[2] Univ Southern Denmark, Dept Phys Chem & Pharm, Campusvej 55, DK-5230 Odense M, Denmark

[3] Newtec Engn AS, DK-5230 Odense, Denmark

[4] Univ Southern Denmark, Mads Clausen Inst, Campusvej 55, DK-5230 Odense M, Denmark

来源：

DISPLAYS | 2022年 / 74卷

关键词：

Hyperspectral cubes reconstruction; Computed tomography imaging spectrometer (CTIS) images; Convolutional neural networks; IMAGING SPECTROMETER; DISTANCE;

D O I：

10.1016/j.displa.2022.102218

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A novel method, utilizing convolutional neural networks (CNNs), is proposed to reconstruct hyperspectral cubes from computed tomography imaging spectrometer (CTIS) images. Current reconstruction algorithms are usually subject to long reconstruction times and mediocre precision in cases of a large number of spectral channels. The constructed CNNs deliver higher precision and shorter reconstruction time than a sparse expectation maximization algorithm. In addition, the network can handle two different types of real-world images at the same fime-specifically ColorChecker and carrot spectral images are considered. This work paves the way toward real-time reconstruction of hyperspectral cubes from CTIS images.

引用

页数：14

共 40 条

[1]

[Anonymous], KERAS

[2]

Bodkin Andrew, 2009, Proceedings of the SPIE - The International Society for Optical Engineering, V7334, DOI 10.1117/12.818929

[3] Hyperspectral imaging: a review of best practice, performance and pitfalls for in-line and on-line applications [J].

Boldrini, Barbara ;

Kessler, Waltraud ;

Rebner, Karsten ;

Kessler, Rudolf W. .

JOURNAL OF NEAR INFRARED SPECTROSCOPY, 2012, 20 (05) :483-508

[4] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[5]

Bulygin T.V., 1992, Proceedings of SPIE, VVolume 1843, P315, DOI DOI 10.1117/12.131904

[6] High Resolution Multispectral Video Capture with a Hybrid Camera System [J].

Cao, Xun ;

Tong, Xin ;

Dai, Qionghai ;

Lin, Stephen .

2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, :297-304

[7] Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network [J].

Chen, Hu ;

Zhang, Yi ;

Kalra, Mannudeep K. ;

Lin, Feng ;

Chen, Yang ;

Liao, Peixi ;

Zhou, Jiliu ;

Wang, Ge .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (12) :2524-2535

[8] COMPUTED-TOMOGRAPHY IMAGING SPECTROMETER - EXPERIMENTAL CALIBRATION AND RECONSTRUCTION RESULTS [J].

DESCOUR, M ;

DERENIAK, E .

APPLIED OPTICS, 1995, 34 (22) :4817-4826

[9]

Douarre C., 2021, CTIS SIMULATOR

[10]

Douarre C., 2021, CTIS DATA SET APPLE

← 1 2 3 4 →