Predicting Protein Content in Grain Using Hyperspectral Deep Learning

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Predicting Protein Content in Grain Using Hyperspectral Deep Learning. / Galbo Engstrøm1, Ole-Christian; Dreier, Erik Schou; Steenstrup Pedersen, Kim.

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . IEEE, 2021. s. 1372-1380.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Galbo Engstrøm1, O-C, Dreier, ES & Steenstrup Pedersen, K 2021, Predicting Protein Content in Grain Using Hyperspectral Deep Learning. i Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . IEEE, s. 1372-1380, 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Virtual, 11/10/2021. https://doi.org/10.1109/ICCVW54120.2021.00158

APA

Galbo Engstrøm1, O-C., Dreier, E. S., & Steenstrup Pedersen, K. (2021). Predicting Protein Content in Grain Using Hyperspectral Deep Learning. I Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (s. 1372-1380). IEEE. https://doi.org/10.1109/ICCVW54120.2021.00158

Vancouver

Galbo Engstrøm1, O-C, Dreier ES, Steenstrup Pedersen K. Predicting Protein Content in Grain Using Hyperspectral Deep Learning. I Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . IEEE. 2021. s. 1372-1380 https://doi.org/10.1109/ICCVW54120.2021.00158

Author

Galbo Engstrøm1, Ole-Christian ; Dreier, Erik Schou ; Steenstrup Pedersen, Kim. / Predicting Protein Content in Grain Using Hyperspectral Deep Learning. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . IEEE, 2021. s. 1372-1380

Bibtex

@inproceedings{2e7c2e91e1714fcb8f7e9c715dfea72b,
title = "Predicting Protein Content in Grain Using Hyperspectral Deep Learning",
abstract = "We assess the possibility of performing regression analysis on hyperspectral images utilizing the entire spatio-spectral data cube in convolutional neural networks using protein regression analysis of bulk wheat grain kernels as a test case. By introducing novel modifications of the well-known convolutional neural network, ResNet-18, we are able to significantly increase its performance on hyperspectral images. Our modifications consist of firstly applying a 3D convolution layer enabling learning of spectral derivatives that 2D spatial convolution is unable to learn, and secondly, the application of a (1 x 1) 2D convolution layer that downsamples the spectral dimension. Analysis of the responses learned by the convolution kernels in our modifications reveals meaningful representations of the input data cube that reduce noise and enable the subsequent ResNet-18 to perform more accurate regression analysis.",
author = "{Galbo Engstr{\o}m1,}, Ole-Christian and Dreier, {Erik Schou} and {Steenstrup Pedersen}, Kim",
year = "2021",
doi = "10.1109/ICCVW54120.2021.00158",
language = "English",
pages = " 1372--1380",
booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)",
publisher = "IEEE",
note = "null ; Conference date: 11-10-2021 Through 17-10-2021",

}

RIS

TY - GEN

T1 - Predicting Protein Content in Grain Using Hyperspectral Deep Learning

AU - Galbo Engstrøm1,, Ole-Christian

AU - Dreier, Erik Schou

AU - Steenstrup Pedersen, Kim

PY - 2021

Y1 - 2021

N2 - We assess the possibility of performing regression analysis on hyperspectral images utilizing the entire spatio-spectral data cube in convolutional neural networks using protein regression analysis of bulk wheat grain kernels as a test case. By introducing novel modifications of the well-known convolutional neural network, ResNet-18, we are able to significantly increase its performance on hyperspectral images. Our modifications consist of firstly applying a 3D convolution layer enabling learning of spectral derivatives that 2D spatial convolution is unable to learn, and secondly, the application of a (1 x 1) 2D convolution layer that downsamples the spectral dimension. Analysis of the responses learned by the convolution kernels in our modifications reveals meaningful representations of the input data cube that reduce noise and enable the subsequent ResNet-18 to perform more accurate regression analysis.

AB - We assess the possibility of performing regression analysis on hyperspectral images utilizing the entire spatio-spectral data cube in convolutional neural networks using protein regression analysis of bulk wheat grain kernels as a test case. By introducing novel modifications of the well-known convolutional neural network, ResNet-18, we are able to significantly increase its performance on hyperspectral images. Our modifications consist of firstly applying a 3D convolution layer enabling learning of spectral derivatives that 2D spatial convolution is unable to learn, and secondly, the application of a (1 x 1) 2D convolution layer that downsamples the spectral dimension. Analysis of the responses learned by the convolution kernels in our modifications reveals meaningful representations of the input data cube that reduce noise and enable the subsequent ResNet-18 to perform more accurate regression analysis.

U2 - 10.1109/ICCVW54120.2021.00158

DO - 10.1109/ICCVW54120.2021.00158

M3 - Article in proceedings

SP - 1372

EP - 1380

BT - Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)

PB - IEEE

Y2 - 11 October 2021 through 17 October 2021

ER -

ID: 287119402