Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform

Edgar Perez-Moreno; Beatriz P. Garcia-Salgado; Volodymyr Ponomaryov; Rogelio Reyes-Reyes; Clara Cruz-Ramos; Denys Ponomaryov

doi:10.1109/PICST51311.2020.9468049

Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform

Edgar Perez-Moreno, Beatriz P. Garcia-Salgado, Volodymyr Ponomaryov, Rogelio Reyes-Reyes, Clara Cruz-Ramos, Denys Ponomaryov

Escuela Superior de Ingeniería Mecánica y Eléctrica (ESIME), Unidad Culhuacán

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Hyperspectral images have many purposes in the industry, the spectral information, which these images provide, allows to perform various sorting or object detection tasks. However, most of these images are obtained at a low-spatial resolution, thus reducing the effectiveness of the tasks, in which they can be used. In this study, a novel framework has been proposed to increase the resolution of hyperspectral images without affecting the spectral properties of the pixels. The designed system consists of two sections: the first section is the spatial section where wavelet transform is used for increasing spatial resolution; the second section represents the spectral procedures where a neural network is employed especially to correct the spectral distortions generated in the spatial section. Numerous experimental results have confirmed the better performance of the novel framework via objective and subjective criteria.

Original language	English
Title of host publication	2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings
Editors	Dmytro Ageyev
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	850-854
Number of pages	5
ISBN (Electronic)	9781728191775
DOIs	https://doi.org/10.1109/PICST51311.2020.9468049
State	Published - 6 Oct 2021
Event	2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Kharkiv, Ukraine Duration: 6 Oct 2020 → 9 Oct 2020

Publication series

Name	2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings

Conference

Conference	2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020
Country/Territory	Ukraine
City	Kharkiv
Period	6/10/20 → 9/10/20

Keywords

Hyperspectral
convolutional neural network
super-resolution
wavelet transform

Access to Document

10.1109/PICST51311.2020.9468049

Cite this

Perez-Moreno, E., Garcia-Salgado, B. P., Ponomaryov, V., Reyes-Reyes, R., Cruz-Ramos, C., & Ponomaryov, D. (2021). Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform. In D. Ageyev (Ed.), 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings (pp. 850-854). Article 9468049 (2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PICST51311.2020.9468049

Perez-Moreno, Edgar ; Garcia-Salgado, Beatriz P. ; Ponomaryov, Volodymyr et al. / Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform. 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings. editor / Dmytro Ageyev. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 850-854 (2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings).

@inproceedings{b26fc03e7a934f059320e14f37da8314,

title = "Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform",

abstract = "Hyperspectral images have many purposes in the industry, the spectral information, which these images provide, allows to perform various sorting or object detection tasks. However, most of these images are obtained at a low-spatial resolution, thus reducing the effectiveness of the tasks, in which they can be used. In this study, a novel framework has been proposed to increase the resolution of hyperspectral images without affecting the spectral properties of the pixels. The designed system consists of two sections: the first section is the spatial section where wavelet transform is used for increasing spatial resolution; the second section represents the spectral procedures where a neural network is employed especially to correct the spectral distortions generated in the spatial section. Numerous experimental results have confirmed the better performance of the novel framework via objective and subjective criteria.",

keywords = "Hyperspectral, convolutional neural network, super-resolution, wavelet transform",

author = "Edgar Perez-Moreno and Garcia-Salgado, {Beatriz P.} and Volodymyr Ponomaryov and Rogelio Reyes-Reyes and Clara Cruz-Ramos and Denys Ponomaryov",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 ; Conference date: 06-10-2020 Through 09-10-2020",

year = "2021",

month = oct,

day = "6",

doi = "10.1109/PICST51311.2020.9468049",

language = "Ingl{\'e}s",

series = "2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "850--854",

editor = "Dmytro Ageyev",

booktitle = "2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings",

address = "Estados Unidos",

}

Perez-Moreno, E, Garcia-Salgado, BP, Ponomaryov, V , Reyes-Reyes, R , Cruz-Ramos, C & Ponomaryov, D 2021, Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform. in D Ageyev (ed.), 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings., 9468049, 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 850-854, 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020, Kharkiv, Ukraine, 6/10/20. https://doi.org/10.1109/PICST51311.2020.9468049

Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform. / Perez-Moreno, Edgar; Garcia-Salgado, Beatriz P.; Ponomaryov, Volodymyr et al.
2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings. ed. / Dmytro Ageyev. Institute of Electrical and Electronics Engineers Inc., 2021. p. 850-854 9468049 (2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform

AU - Perez-Moreno, Edgar

AU - Garcia-Salgado, Beatriz P.

AU - Ponomaryov, Volodymyr

AU - Reyes-Reyes, Rogelio

AU - Cruz-Ramos, Clara

AU - Ponomaryov, Denys

PY - 2021/10/6

Y1 - 2021/10/6

N2 - Hyperspectral images have many purposes in the industry, the spectral information, which these images provide, allows to perform various sorting or object detection tasks. However, most of these images are obtained at a low-spatial resolution, thus reducing the effectiveness of the tasks, in which they can be used. In this study, a novel framework has been proposed to increase the resolution of hyperspectral images without affecting the spectral properties of the pixels. The designed system consists of two sections: the first section is the spatial section where wavelet transform is used for increasing spatial resolution; the second section represents the spectral procedures where a neural network is employed especially to correct the spectral distortions generated in the spatial section. Numerous experimental results have confirmed the better performance of the novel framework via objective and subjective criteria.

AB - Hyperspectral images have many purposes in the industry, the spectral information, which these images provide, allows to perform various sorting or object detection tasks. However, most of these images are obtained at a low-spatial resolution, thus reducing the effectiveness of the tasks, in which they can be used. In this study, a novel framework has been proposed to increase the resolution of hyperspectral images without affecting the spectral properties of the pixels. The designed system consists of two sections: the first section is the spatial section where wavelet transform is used for increasing spatial resolution; the second section represents the spectral procedures where a neural network is employed especially to correct the spectral distortions generated in the spatial section. Numerous experimental results have confirmed the better performance of the novel framework via objective and subjective criteria.

KW - Hyperspectral

KW - convolutional neural network

KW - super-resolution

KW - wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=85114439776&partnerID=8YFLogxK

U2 - 10.1109/PICST51311.2020.9468049

DO - 10.1109/PICST51311.2020.9468049

M3 - Contribución a la conferencia

AN - SCOPUS:85114439776

T3 - 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings

SP - 850

EP - 854

BT - 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings

A2 - Ageyev, Dmytro

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020

Y2 - 6 October 2020 through 9 October 2020

ER -

Perez-Moreno E, Garcia-Salgado BP, Ponomaryov V , Reyes-Reyes R , Cruz-Ramos C, Ponomaryov D. Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform. In Ageyev D, editor, 2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 850-854. 9468049. (2020 IEEE International Conference on Problems of Infocommunications Science and Technology, PIC S and T 2020 - Proceedings). doi: 10.1109/PICST51311.2020.9468049

Hyperspectral Image Super-Resolution Using Convolutional Neural Network and Wavelet Transform

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this