TY - GEN

T1 - Improving Deep Learning on Hyperspectral Images of Grain by Incorporating Domain Knowledge from Chemometrics

AU - Engstrøm, Ole-Christian Galbo

AU - Dreier, Erik Schou

AU - Jespersen, Birthe P Møller

AU - Steenstrup Pedersen, Kim

PY - 2023

Y1 - 2023

N2 - We demonstrate how to design and apply domain-specific modifications to convolutional neural networks (CNNs) to improve model performance on hyperspectral images of grain kernels. We use hyperspectral images of grain kernels captured in the near-infrared wavelength range of 900 to 1700 nm as a case for supporting our argumentation. This part of the electromagnetic spectrum contains convoluted signals with chemical and physical information relevant to grain quality. For standard chemometric models, domain knowledge is used to select from a plethora of combinations of preprocessing techniques helpful in extracting relevant chemical and physical features for a given task. By incorporating domain-specific design modifications in the preexisting architectures of ResNet-18 and a simple CNN, we show that model performance can be increased significantly and that applying domain knowledge to CNNs is much more important than complexity is to their performance.

AB - We demonstrate how to design and apply domain-specific modifications to convolutional neural networks (CNNs) to improve model performance on hyperspectral images of grain kernels. We use hyperspectral images of grain kernels captured in the near-infrared wavelength range of 900 to 1700 nm as a case for supporting our argumentation. This part of the electromagnetic spectrum contains convoluted signals with chemical and physical information relevant to grain quality. For standard chemometric models, domain knowledge is used to select from a plethora of combinations of preprocessing techniques helpful in extracting relevant chemical and physical features for a given task. By incorporating domain-specific design modifications in the preexisting architectures of ResNet-18 and a simple CNN, we show that model performance can be increased significantly and that applying domain knowledge to CNNs is much more important than complexity is to their performance.

U2 - 10.1109/ICCVW60793.2023.00055

DO - 10.1109/ICCVW60793.2023.00055

M3 - Article in proceedings

SN - 979-8-3503-0745-0

SP - 485

EP - 494

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

PB - IEEE

Y2 - 2 October 2023 through 6 October 2023

ER -