Predicting Protein Content in Grain Using Hyperspectral Deep Learning

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

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.
OriginalsprogEngelsk
TitelProceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)
ForlagIEEE
Publikationsdato2021
Sider 1372-1380
DOI
StatusUdgivet - 2021
Begivenhed2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) - Virtual
Varighed: 11 okt. 202117 okt. 2021

Konference

Konference2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
ByVirtual
Periode11/10/202117/10/2021

Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk


Ingen data tilgængelig

ID: 287119402