Adversarial Large-Scale Root Gap Inpainting

Chen, Hao; Giuffrida, Mario Valerio; Doerner, Peter; Tsaftaris, Sotirios A.

doi:10.1109/cvprw.2019.00318

Cited by 15 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7, the CNN would leave gaps when a root was covered by large amounts of soil. An approach such as [84] could be used to recover such gaps which may improve the biological relevance of our root length estimates and potentially facilitate the extraction of more detailed root architecture information.…”

Section: Discussionmentioning

confidence: 99%

Segmentation of roots in soil with U-Net

et al. 2020

View full text Add to dashboard Cite

Background Plant root research can provide a way to attain stress-tolerant crops that produce greater yield in a diverse array of conditions. Phenotyping roots in soil is often challenging due to the roots being difficult to access and the use of time consuming manual methods. Rhizotrons allow visual inspection of root growth through transparent surfaces. Agronomists currently manually label photographs of roots obtained from rhizotrons using a line-intersect method to obtain root length density and rooting depth measurements which are essential for their experiments. We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements. We design a data-set of 50 annotated chicory (Cichorium intybus L.) root images which we use to train, validate and test the system and compare against a baseline built using the Frangi vesselness filter. We obtain metrics using manual annotations and line-intersect counts. Results Our results on the held out data show our proposed automated segmentation system to be a viable solution for detecting and quantifying roots. We evaluate our system using 867 images for which we have obtained line-intersect counts, attaining a Spearman rank correlation of 0.9748 and an $$r^2$$r2 of 0.9217. We also achieve an $$F_1$$F1 of 0.7 when comparing the automated segmentation to the manual annotations, with our automated segmentation system producing segmentations with higher quality than the manual annotations for large portions of the image. Conclusion We have demonstrated the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method. The success of our approach is also a demonstration of the feasibility of deep learning in practice for small research groups needing to create their own custom labelled dataset from scratch.

show abstract

Section: Discussionmentioning

confidence: 99%

Segmentation of roots in soil with U-Net

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Advances in machine learning applied to image analysis allowed partially overcoming these limitations. For example, deep learning techniques have been used to improve the consistency of classic approaches enhancing the quality of root segmentations [44, 45]. Closest to our work is the recent RootNav 2 [46], which is also based on deep learning models and provides fine-grained metrics distinguishing between MR and LRs.…”

Section: Discussionmentioning

confidence: 99%

ChronoRoot: High-throughput phenotyping by deep segmentation networks reveals novel temporal parameters of plant root system architecture

Gaggion

Ariel

Daric

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning methods have outperformed previous techniques in most computer vision tasks, including image-based plant phenotyping. However, massive data collection of root traits and the development of associated artificial intelligence approaches have been hampered by the inaccessibility of the rhizosphere. Here we present ChronoRoot, a system which combines 3D printed open-hardware with deep segmentation networks for high temporal resolution phenotyping of plant roots in agarized medium. We developed a novel deep learning based root extraction method which leverages the latest advances in convolutional neural networks for image segmentation, and incorporates temporal consistency into the root system architecture reconstruction process. Automatic extraction of phenotypic parameters from sequences of images allowed a comprehensive characterization of the root system growth dynamics. Furthermore, novel time-associated parameters emerged from the analysis of spectral features derived from temporal signals. Altogether, our work shows that the combination of machine intelligence methods and a 3D-printed device expands the possibilities of root high-throughput phenotyping for genetics and natural variation studies as well as the screening of clock-related mutants, revealing novel root traits.

show abstract

“…With accurate RSA segmentations, many existing RSA analysis methods can be used to calculate important root phenotypic traits for analysis. CNN-based RSA segmentation methods also faced the challenge of limited annotated training images, so researchers tried to generate synthetic images for model training [ 125 , 126 ].…”

Section: Cnn-based Analytical Approaches For Image-based Plant Phementioning

confidence: 99%

“…Experimental results showed that measurement accuracies of root phenotypic traits (tip length and number) using corrected segmentations increased 2 to 5 times than those using the raw segmentations. A following study further expanded the model by adding adversarial module at the patch and global levels [ 125 ]. The adversarial module helped the model to learn robust feature representations for root tip inpainting, and the two-level training helped the model to produce accurate results both locally (image patches) and globally (the whole root image).…”

Section: Cnn-based Analytical Approaches For Image-based Plant Phementioning

confidence: 99%

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

2020

Plant Phenomics

251

180

View full text Add to dashboard Cite

Plant phenotyping has been recognized as a bottleneck for improving the efficiency of breeding programs, understanding plant-environment interactions, and managing agricultural systems. In the past five years, imaging approaches have shown great potential for high-throughput plant phenotyping, resulting in more attention paid to imaging-based plant phenotyping. With this increased amount of image data, it has become urgent to develop robust analytical tools that can extract phenotypic traits accurately and rapidly. The goal of this review is to provide a comprehensive overview of the latest studies using deep convolutional neural networks (CNNs) in plant phenotyping applications. We specifically review the use of various CNN architecture for plant stress evaluation, plant development, and postharvest quality assessment. We systematically organize the studies based on technical developments resulting from imaging classification, object detection, and image segmentation, thereby identifying state-of-the-art solutions for certain phenotyping applications. Finally, we provide several directions for future research in the use of CNN architecture for plant phenotyping purposes.

show abstract

Adversarial Large-Scale Root Gap Inpainting

Cited by 15 publications

References 24 publications

Segmentation of roots in soil with U-Net

Segmentation of roots in soil with U-Net

ChronoRoot: High-throughput phenotyping by deep segmentation networks reveals novel temporal parameters of plant root system architecture

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

Contact Info

Product

Resources

About