Determination of wheat spike and spikelet architecture and grain traits using X-ray Computed Tomography imaging

Zhou, Hu; Riche, A. B.; Hawkesford, Malcolm J.; Whalley, W. R.; Atkinson, Brian S.; Sturrock, Craig J.; Mooney, Sacha J.

doi:10.1186/s13007-021-00726-5

Cited by 25 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such cases the "virtual shelling” enabled by X-ray technology could largely offset these hurdles. X-ray scanning is also suitable for evaluation of whole panicles (cereals) or pods (legumes) where it can offset the laborious process of grain threshing as shown before [ 20 , 21 , 25 , 34 , 35 , 42 ]. Also X-ray can be used for non-destructive evaluation of inner structures and physical properties of the grains, tubers etc.…”

Section: Discussionmentioning

confidence: 99%

X-ray driven peanut trait estimation: computer vision aided agri-system transformation

et al. 2022

View full text Add to dashboard Cite

Background In India, raw peanuts are obtained by aggregators from smallholder farms in the form of whole pods and the price is based on a manual estimation of basic peanut pod and kernel characteristics. These methods of raw produce evaluation are slow and can result in procurement irregularities. The procurement delays combined with the lack of storage facilities lead to fungal contaminations and pose a serious threat to food safety in many regions. To address this gap, we investigated whether X-ray technology could be used for the rapid assessment of the key peanut qualities that are important for price estimation. Results We generated 1752 individual peanut pod 2D X-ray projections using a computed tomography (CT) system (CTportable160.90). Out of these projections we predicted the kernel weight and shell weight, which are important indicators of the produce price. Two methods for the feature prediction were tested: (i) X-ray image transformation (XRT) and (ii) a trained convolutional neural network (CNN). The prediction power of these methods was tested against the gravimetric measurements of kernel weight and shell weight in diverse peanut pod varieties1. Both methods predicted the kernel mass with R2 > 0.93 (XRT: R2 = 0.93 and mean error estimate (MAE) = 0.17, CNN: R2 = 0.95 and MAE = 0.14). While the shell weight was predicted more accurately by CNN (R2 = 0.91, MAE = 0.09) compared to XRT (R2 = 0.78; MAE = 0.08). Conclusion Our study demonstrated that the X-ray based system is a relevant technology option for the estimation of key peanut produce indicators (Figure 1). The obtained results justify further research to adapt the existing X-ray system for the rapid, accurate and objective peanut procurement process. Fast and accurate estimates of produce value are a necessary pre-requisite to avoid post-harvest losses due to fungal contamination and, at the same time, allow the fair payment to farmers. Additionally, the same technology could also assist crop improvement programs in selecting and developing peanut cultivars with enhanced economic value in a high-throughput manner by skipping the shelling of the pods completely. This study demonstrated the technical feasibility of the approach and is a first step to realize a technology-driven peanut production system transformation of the future.

show abstract

Section: Discussionmentioning

confidence: 99%

X-ray driven peanut trait estimation: computer vision aided agri-system transformation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In spite of the fact that the current advanced technology of X-ray computed tomography has provided almost any kind of data required for geometric assessment of wheat grain e.g. see [ 15 – 18 ], utilizing this approach is time consuming, expensive, and limited to comparatively less available specific CT scanners. Moreover, reconstruction and analysis of 3D structures requires a more sophisticated level of image processing.…”

Section: Introductionmentioning

confidence: 99%

Wheat grain width: a clue for re-exploring visual indicators of grain weight

2022

View full text Add to dashboard Cite

Background Mean grain weight (MGW) is among the most frequently measured parameters in wheat breeding and physiology. Although in the recent decades, various wheat grain analyses (e.g. counting, and determining the size, color, or shape features) have been facilitated, thanks to the automated image processing systems, MGW estimations have been limited to using few number of image-derived indices; i.e. mainly the linear or power models developed based on the projected area (Area). Following a preliminary observation which indicated the potential of grain width in improving the predictions, the present study was conducted to explore more efficient indices for increasing the precision of image-based MGW estimations. For this purpose, an image archive of the grains was processed, which were harvested from a 2-year field experiment carried out with 3 replicates under two irrigation conditions and included 15 cultivar mixture treatments (so the archive was consisted of 180 images including more than 72,000 grains). Results It was observed that among the more than 30 evaluated indices of grain size and shape, indicators of grain width (i.e. Minor & MinFeret) along with 8 other empirical indices had a higher correlation with MGW, compared with Area. The most precise MGW predictions were obtained using the Area × Circularity, Perimeter × Circularity, and Area/Perimeter indices. Furthermore, it was found that (i) grain width and the Area/Perimeter ratio were the common factors in the structure of the superior predictive indices; and (ii) the superior indices had the highest correlation with grain width, rather than with their mathematical components. Moreover, comparative efficiency of the superior indices almost remained stable across the 4 environmental conditions. Eventually, using the selected indices, ten simple linear models were developed and validated for MGW prediction, which indicated a relatively higher precision than the current Area-based models. The considerable effect of enhancing image resolution on the precision of the models has been also evidenced. Conclusions It is expected that the findings of the present study, along with the simple predictive linear models developed and validated using new image-derived indices, could improve the precision of the image-based MGW estimations, and consequently facilitate wheat breeding and physiological assessments.

show abstract

“…Furthermore, X-ray and CT imaging have been explored to non-destructively measure phenotypic traits of wheat spikes. Both X-ray and CT imaging can measure the inner structures of spikes and acquire information on grains (Duan et al, 2011 ; Xiong et al, 2019a ; Yu et al, 2021 ), which can be further used to distinguish and count the filled spikelets (Zhou et al, 2021 ). As for CT imaging, it can reconstruct spikes in three dimensions as well.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection and Counting of Wheat Spikelet Using Semi-Automatic Labeling and Deep Learning

Zhang

2022

Front. Plant Sci.

View full text Add to dashboard Cite

The number of wheat spikelets is an important phenotypic trait and can be used to assess the grain yield of the wheat crop. However, manual counting of spikelets is time-consuming and labor-intensive. To develop a cost-effective and highly efficient phenotyping system for counting the number of spikelets under laboratory conditions, methods based on imaging processing techniques and deep learning were proposed to accurately detect and count spikelets from color images of wheat spikes captured at the grain filling stage. An unsupervised learning-based method was first developed to automatically detect and label spikelets from spike color images and build the datasets for the model training. Based on the constructed datasets, a deep convolutional neural network model was retrained using transfer learning to detect the spikelets. Testing results showed that the root mean squared errors, relative root mean squared errors, and the coefficients of determination between the automatic and manual counted spikelets for four wheat lines were 0.62, 0.58, 0.54, and 0.77; 3.96, 3.73, 3.34, and 4.94%; and 0.73, 0.78, 0.84, and 0.67, respectively. We demonstrated that the proposed methods can effectively estimate the number of wheat spikelets, which improves the counting efficiency of wheat spikelets and contributes to the analysis of the developmental characteristics of wheat spikes.

show abstract

Determination of wheat spike and spikelet architecture and grain traits using X-ray Computed Tomography imaging

Cited by 25 publications

References 19 publications

X-ray driven peanut trait estimation: computer vision aided agri-system transformation

X-ray driven peanut trait estimation: computer vision aided agri-system transformation

Wheat grain width: a clue for re-exploring visual indicators of grain weight

Automatic Detection and Counting of Wheat Spikelet Using Semi-Automatic Labeling and Deep Learning

Contact Info

Product

Resources

About