Automatic and Accurate Calculation of Rice Seed Setting Rate Based on Image Segmentation and Deep Learning

Guo, Yixin; Li, Shuai; Zhang, Zhanguo; Yang, Li; Hu, Zhenbang; Xin, Dawei; Chen, Qingshan; Wang, Jingguo; Zhu, Rihong

doi:10.3389/fpls.2021.770916

Cited by 10 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All statistical values calculated from the confusion matrix, which have true positive (TP), false positive (FP), true negative (TN) and false negative (FN). Each statistical value has the following details [21] [22].…”

Section: Experiments Resultsmentioning

confidence: 99%

Image-to-Video Retrieval by ResNet50

Pornpanomchai

2023

ijmst

View full text Add to dashboard Cite

The objective of this research is to create a computer system which can retrieve a video clip by using only a single image. The developed system is called “Image-to-Video Retrieval System (I2VRS)”. The system employs the convolutional neural networks called “ResNet50”, which is a toolbox in MATLAB software to retrieve the video clip dataset. The ResNet50 is one of the powerful CNN to recognize an image in the image processing technique. The I2VRS creates its own dataset called I2VRS dataset, which consists of 101 video clips and each video clip contains 1,000 video frames. All video clips are filmed around 60 s. each in the .MP4 file-format. The system also tests an un-training dataset with 100 images, which are directly taken with a mobile phone in the .JPEG file-format. The mean average precision (mAP) of the system is 0.9825, with the training dataset time being 5,668.7 s. The average access time to retrieve a video clip is 1.5726 s. per image.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Image-to-Video Retrieval by ResNet50

Pornpanomchai

2023

ijmst

View full text Add to dashboard Cite

show abstract

“…The empty shell number, 1000‐seed weight, and full grain number of rice were measured as previously described. [ 74 ] Total grain number per plant = full grain number per plant + empty shell number per plant; Seed setting rate (%) = full grain number per plant/total grain number per plant × 100; Yield per plant (g) = full grain number per plant × 1000‐seed weight /1000. Ten replicates were shown for plant height and other phenotypic analysis, and from them three replicates selected randomly were shown for physiological, and biochemical analysis.…”

Section: Methodsmentioning

confidence: 99%

Evidence and Impacts of Nanoplastic Accumulation on Crop Grains

Jiang

Wang

et al. 2022

Advanced Science

View full text Add to dashboard Cite

Nanoplastics are emerging pollutants of global concern. Agricultural soil is becoming a primary sink for nanoplastics generated from plastic debris. The uptake and accumulation of nanoplastics by crops contaminate the food chain and pose unexpected risks to human health. However, whether nanoplastics can enter grains and their impact on the grains of crop grown in contaminated soil is still unknown. Here, the translocation of polystyrene nanoplastics (PS-NPs) in crops, including peanut (Arachis hypogaea L.) and rice (Oryza sativa L.) is investigated. It is demonstrated PS-NPs translocation from the root and accumulation in the grains at the maturation stage. The treatment with PS-NPs (250 mg kg −1 ) increases the empty-shell numbers of rice grain by 35.45%, thereby decreasing the seed-setting rate of rice by 3.02%, and also decreases the average seed weight of peanuts by 3.45%. Moreover, PS-NPs exerted adverse effects on nutritional quality, such as decreasing the content of mineral elements, amino acids, and unsaturated fatty acids. To the knowledge, this is the first report of the presence of nanoplastics in the grains of crop plants grown in soil containing nanoplastics, and the results highlight the impact of nanoplastics on the yield and nutritional quality of crop grains.

show abstract

“…CI rice showed greater root activity compared to FI; thus, the rice root dry matter under CI was higher [33]. The SR of rice is an important component of yield, and improving the SR can directly increase the number of grains per ear, causing yield to increase [34]. The SR and IWUE had the highest CS values of 0.81 and 2.42, respectively (Table 2), because straw returning increased the activities of ADPG of grain in middle and late grain filling owing to improving the SR and grain weight, causing the yield to increase (Figure 5); in addition, CI can reduce water.…”

Section: Effects Of Irrigation and Fertilization Management On Yieldmentioning

confidence: 99%

Effects of Irrigation and Fertilization Management on Yield and Quality of Rice and the Establishment of a Quality Evaluation System

Hu,

Zhang,

Yang

et al. 2023

Agronomy

View full text Add to dashboard Cite

Yield and rice quality indicators of crops are a direct reflection of the rational irrigation and fertilizer strategy. However, the effects of controlled irrigation (CI) combined with the split application of fertilization managements (straw returning, organic fertilizer, and conventional fertilizer) on rice quality are not clear in southeast China. This study aims at exploring the effects of three fertilization managements applied under CI or flooding irrigation on rice yield, quality, enzyme activity, and soluble sugar content including 43 indicators, to determine the optimal comprehensive evaluation model, management, and representative indexes. The results showed that compared with CF (CI + conventional fertilizer), CS (CI + straw returning) significantly increased yield (27.65%), irrigation water use efficiency (6.20%), chalky grain rate (9.67%), chalkiness (1.83%), protein content (4.29%), and amylose content (0.33%), indicating that CS improved yield and milling quality but decreased cooking and appearance quality. This was mainly because CS promoted the activities of alpha-amylase, ADPG (ADP-glucose pyrophosphorylase), and GBSS (granule-bound starch synthase) and reduced the soluble sugar content in rice. Grey relational degree analysis (GRD), the entropy method (ETM), and TOPSIS (the technique for order preference by similarity to an ideal solution) were used to comprehensively evaluate the rice quality and determined that CS treatments could synergistically improve yield and rice quality. The five indexes (adhesive strength, HPV, ADPG, soluble sugar (leaf), yield) and TOPSIS model can be used as the best indexes and model to evaluate the rice quality. These results could provide scientific management and evaluate practices for high-yield and high-quality rice cultivation, which may be promising for a cleaner production strategy.

show abstract

Automatic and Accurate Calculation of Rice Seed Setting Rate Based on Image Segmentation and Deep Learning

Cited by 10 publications

References 35 publications

Image-to-Video Retrieval by ResNet50

Image-to-Video Retrieval by ResNet50

Evidence and Impacts of Nanoplastic Accumulation on Crop Grains

Effects of Irrigation and Fertilization Management on Yield and Quality of Rice and the Establishment of a Quality Evaluation System

Contact Info

Product

Resources

About