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

He, Yong; Zhang, Man

doi:10.3389/fpls.2022.872555

Cited by 16 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work by (Qiu et al, 2022) is aimed at the problem of spikelet detection on images of spikes against a white background. Before spikelet detection, the images were segmented into spike and background.…”

Section: Related Workmentioning

confidence: 99%

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Artemenko,

Genaev,

Epifanov

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionPubescence is an important phenotypic trait observed in both vegetative and generative plant organs. Pubescent plants demonstrate increased resistance to various environmental stresses such as drought, low temperatures, and pests. It serves as a significant morphological marker and aids in selecting stress-resistant cultivars, particularly in wheat. In wheat, pubescence is visible on leaves, leaf sheath, glumes and nodes. Regarding glumes, the presence of pubescence plays a pivotal role in its classification. It supplements other spike characteristics, aiding in distinguishing between different varieties within the wheat species. The determination of pubescence typically involves visual analysis by an expert. However, methods without the use of binocular loupe tend to be subjective, while employing additional equipment is labor-intensive. This paper proposes an integrated approach to determine glume pubescence presence in spike images captured under laboratory conditions using a digital camera and convolutional neural networks.MethodsInitially, image segmentation is conducted to extract the contour of the spike body, followed by cropping of the spike images to an equal size. These images are then classified based on glume pubescence (pubescent/glabrous) using various convolutional neural network architectures (Resnet-18, EfficientNet-B0, and EfficientNet-B1). The networks were trained and tested on a dataset comprising 9,719 spike images.ResultsFor segmentation, the U-Net model with EfficientNet-B1 encoder was chosen, achieving the segmentation accuracy IoU = 0.947 for the spike body and 0.777 for awns. The classification model for glume pubescence with the highest performance utilized the EfficientNet-B1 architecture. On the test sample, the model exhibited prediction accuracy parameters of F1 = 0.85 and AUC = 0.96, while on the holdout sample it showed F1 = 0.84 and AUC = 0.89. Additionally, the study investigated the relationship between image scale, artificial distortions, and model prediction performance, revealing that higher magnification and smaller distortions yielded a more accurate prediction of glume pubescence.

show abstract

Section: Related Workmentioning

confidence: 99%

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Artemenko,

Genaev,

Epifanov

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…For example, in a rice panicle phenotyping study, it was observed that the manual shaping of spikelet was required to improve the prediction correlation using RGB images obtained from a smartphone (Yu et al, 2021). Similarly, Qiu et al (2022) reported that lateral florets of wheat were misclassified as wheat spikelet, required manual correction. ML models are yet to be effective in detecting the small structures of MFCs.…”

Section: Data Classificationmentioning

confidence: 99%

“…ML algorithms do not consider preconceived relationships but make predictions by learning from the input data. Therefore, ML is still prone to misclassification as it is unable to distinguish between correlation and causation (Qiu et al., 2022). For example, in a rice panicle phenotyping study, it was observed that the manual shaping of spikelet was required to improve the prediction correlation using RGB images obtained from a smartphone (Yu et al., 2021).…”

Section: Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for major food crops breeding: Applications, challenges, and ways forward

et al. 2023

View full text Add to dashboard Cite

Increasing the production of the three major food crops (MFCs), maize (Zea mays), rice (Oryza sativa), and wheat (Triticum aestivum), is essential to fulfilling the food demand for the growing human population. Increasing food production may require the integration of machine learning (ML) into plant breeding programs. However, developing ML tools to improve the production of MFCs is a daunting task due to the lack of quality data and the computation resources needed to process this information. Hence, this review discusses the recent applications of ML for improving MFCs production, including plant phenotyping, yield forecasting, and candidate gene prediction. Based on the challenges reported in recent ML experiments for MFCs, this review prescribes solutions to produce scalable ML models. This review provides valuable insights for future studies and promotes collective efforts among researchers implementing ML to enhance MFCs productivity.

show abstract

“…Image processing and machine learning development has provided an important monitoring tool for segmenting and recognizing wheat and spike grain counts [ 8 ]. Although image processing techniques are widely used to identify the number of wheat ears and grains, there are still efficiency and practical application issues due to the extraction of texture, color, and morphological features.…”

Section: Introductionmentioning

confidence: 99%

Segmentation and counting of wheat spike grains based on deep learning and textural feature

Qian

Feng

et al. 2023

Plant Methods

View full text Add to dashboard Cite

Background Grain count is crucial to wheat yield composition and estimating yield parameters. However, traditional manual counting methods are time-consuming and labor-intensive. This study developed an advanced deep learning technique for the segmentation counting model of wheat grains. This model has been rigorously tested on three distinct wheat varieties: ‘Bainong 307’, ‘Xinmai 26’, and ‘Jimai 336’, and it has achieved unprecedented predictive counting accuracy. Method The images of wheat ears were taken with a smartphone at the late stage of wheat grain filling. We used image processing technology to preprocess and normalize the images to 480*480 pixels. A CBAM-HRNet wheat grain segmentation counting deep learning model based on the Convolutional Block Attention Module (CBAM) was constructed by combining deep learning, migration learning, and attention mechanism. Image processing algorithms and wheat grain texture features were used to build a grain counting and predictive counting model for wheat grains. Results The CBAM-HRNet model using the CBAM was the best for wheat grain segmentation. Its segmentation accuracy of 92.04%, the mean Intersection over Union (mIoU) of 85.21%, the category mean pixel accuracy (mPA) of 91.16%, and the recall rate of 91.16% demonstrate superior robustness compared to other models such as HRNet, PSPNet, DeeplabV3+ , and U-Net. Method I for spike count, which calculates twice the number of grains on one side of the spike to determine the total number of grains, demonstrates a coefficient of determination R2 of 0.85, a mean absolute error (MAE) of 1.53, and a mean relative error (MRE) of 2.91. In contrast, Method II for spike count involves summing the number of grains on both sides to determine the total number of grains, demonstrating a coefficient of determination R2 of 0.92, an MAE) of 1.15, and an MRE) of 2.09%. Conclusions Image segmentation algorithm of the CBAM-HRNet wheat spike grain is a powerful solution that uses the CBAM to segment wheat spike grains and obtain richer semantic information. This model can effectively address the challenges of small target image segmentation and under-fitting problems in training. Additionally, the spike grain counting model can quickly and accurately predict the grain count of wheat, providing algorithmic support for efficient and intelligent wheat yield estimation.

show abstract

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

Cited by 16 publications

References 29 publications

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Machine learning for major food crops breeding: Applications, challenges, and ways forward

Segmentation and counting of wheat spike grains based on deep learning and textural feature

Contact Info

Product

Resources

About