Next Article in Journal
Comparing DInSAR and PSI Techniques Employed to Sentinel-1 Data to Monitor Highway Stability: A Case Study of a Massive Dobkovičky Landslide, Czech Republic
Previous Article in Journal
Self-Adjusting Thresholding for Burnt Area Detection Based on Optical Images
Open AccessArticle

Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN

1
Department of Engineering, Aarhus University, Finlandsgade 22, DK-8200 Aarhus N, Denmark
2
Department of Agroecology, Aarhus University, Forsøgsvej 1, DK-4200 Slagelse, Denmark
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(22), 2671; https://doi.org/10.3390/rs11222671
Received: 7 October 2019 / Revised: 6 November 2019 / Accepted: 13 November 2019 / Published: 15 November 2019
(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
Lack of annotated data for training of deep learning systems is a challenge for many visual recognition tasks. This is especially true for domain-specific applications, such as plant detection and recognition, where the annotation process can be both time-consuming and error-prone. Generative models can be used to alleviate this issue by producing artificial data that mimic properties of real data. This work presents a semi-supervised generative adversarial network (GAN) model to produce artificial samples of plant seedlings. By applying the semi-supervised approach, we are able to produce visually distinct samples for nine unique plant species using a single GAN model, while still maintaining a relatively high visual variance in the produced samples for each species. Additionally, we are able to control the appearance of the generated samples with respect to rotation and size through a set of latent variables, despite these not being annotated features in the training data. The generated samples resemble the intended species with an average recognition accuracy of ∼64.3%, evaluated using an external state-of-the-art plant seedling classification model. Additionally, we explore the potential of using the GAN model’s discriminator as a quality assessment tool to remove poor representations of plant seedlings from the artificial samples. View Full-Text
Keywords: generative model; generative adversarial networks; supervised learning; unsupervised learning generative model; generative adversarial networks; supervised learning; unsupervised learning
Show Figures

Graphical abstract

MDPI and ACS Style

Madsen, S.L.; Mortensen, A.K.; Jørgensen, R.N.; Karstoft, H. Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN. Remote Sens. 2019, 11, 2671. https://doi.org/10.3390/rs11222671

AMA Style

Madsen SL, Mortensen AK, Jørgensen RN, Karstoft H. Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN. Remote Sensing. 2019; 11(22):2671. https://doi.org/10.3390/rs11222671

Chicago/Turabian Style

Madsen, Simon L.; Mortensen, Anders K.; Jørgensen, Rasmus N.; Karstoft, Henrik. 2019. "Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN" Remote Sens. 11, no. 22: 2671. https://doi.org/10.3390/rs11222671

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop