Advancement of non-destructive spectral measurements for the quality of major tropical fruits and vegetables: a review

Frontiers in Plant Science, Journal Year: 2023, Volume and Issue: 14

Published: Aug. 16, 2023

The quality of tropical fruits and vegetables the expanding global interest in eating healthy foods have resulted continual development reliable, quick, cost-effective assurance methods. present review discusses advancement non-destructive spectral measurements for evaluating major vegetables. Fourier transform infrared (FTIR), Near-infrared (NIR), Raman spectroscopy, hyperspectral imaging (HSI) were used to monitor external internal parameters papaya, pineapple, avocado, mango, banana. ability HSI detect both spatial dimensions proved its efficiency measuring qualities such as grading 516 bananas, defects 10 mangoes avocados with 98.45%, 97.95%, 99.9%, respectively. All techniques effectively assessed characteristics total soluble solids (TSS), solid content (SSC), moisture (MC), exception NIR, which was found limited penetration depth thick rinds or skins, including appropriate selection NIR optical geometry wavelength range can help improve prediction accuracy these crops. combined machine learning deep technologies increased estimating six maturity stages papaya fruit, from unripe overripe stages, F1 scores up 0.90 by feature concatenation data developed visible light. presented findings technological advancements offer promising

Language: Английский

---

A Survey of Computer Vision Technologies in Urban and Controlled-environment Agriculture

ACM Computing Surveys, Journal Year: 2023, Volume and Issue: 56(5), P. 1 - 39

Published: Oct. 3, 2023

In the evolution of agriculture to its next stage, Agriculture 5.0, artificial intelligence will play a central role. Controlled-environment agriculture, or CEA, is special form urban and suburban agricultural practice that offers numerous economic, environmental, social benefits, including shorter transportation routes population centers, reduced environmental impact, increased productivity. Due ability control factors, CEA couples well with computer vision (CV) in adoption real-time monitoring plant conditions autonomous cultivation harvesting. The objective this article familiarize CV researchers applications practitioners solutions offered by CV. We identify five major analyze their requirements motivation, survey state-of-the-art as reflected 68 technical papers using deep learning methods. addition, we discuss key subareas how they related these problems, 14 vision-based datasets. hope help quickly gain bird’s-eye view striving research area spark inspiration for new development.

Language: Английский

---

Automating Seedling Counts in Horticulture Using Computer Vision and AI

Horticulturae, Journal Year: 2023, Volume and Issue: 9(10), P. 1134 - 1134

Published: Oct. 14, 2023

The accelerated growth of computer vision techniques (CVT) has allowed their application in various disciplines, including horticulture, facilitating the work producers, reducing costs, and improving quality life. These have made it possible to contribute automation agro-industrial processes, avoiding excessive visual fatigue when undertaking repetitive tasks, such as monitoring selecting seedlings grown trays. In this study, an object detection model a mobile were developed that be counted from images calculation number per tray. This system was under CRISP-DM methodology improve capture information, data processing, training models using six crops four types Subsequently, experimental test carried out verify integration both parts unified system, reaching efficiency between 57% 96% counting process.

Language: Английский

---

Vine variety identification through leaf image classification: a large-scale study on the robustness of five deep learning models

The Journal of Agricultural Science, Journal Year: 2024, Volume and Issue: 162(1), P. 19 - 32

Published: Feb. 1, 2024

Abstract Varietal identification plays a pivotal role in viticulture for several purposes. Nowadays, such is accomplished using ampelography and molecular markers, techniques requiring specific expertise equipment. Deep learning, on the other hand, appears to be viable cost-effective alternative, as recent studies claim that computer vision models can identify different vine varieties with high accuracy. Such works, however, limit their scope handful of selected do not provide accurate figures external data validation. In current study, five well-known were applied leaf images verify whether results presented literature replicated over larger set consisting 27 26 382 images. It was built 2 years dedicated field sampling at three geographically distinct sites, validation collected from Internet. Cross-validation purpose-built confirm results. However, same models, when validated against independent set, appear unable generalize training retain performances measured during cross These indicate further enhancement have been done filling gap developing more reliable model discriminate among grape varieties, underlining that, achieve this purpose, image resolution crucial factor development models.

Language: Английский

---

Innovative Hybrid Deep Learning Strategy for Detecting and Classifying White Rot in Onions

2022 IEEE 7th International conference for Convergence in Technology (I2CT), Journal Year: 2024, Volume and Issue: unknown

Published: April 5, 2024

The disease severity of onion white rot has to be measured carefully and correctly ensure proper agricultural management this crop. It is one the most threatening diseases affecting onions since it caused by fungal organism called Sclerotium cepivourum. This imperative calls for research we introduce, a novel hybrid model combining ability Convolutional Neural Networks (CNN) with explained decision tree (DT). symbiotic integration tries enhance precision classifying intensity fine-tuned automated diagnosis. Our study based on custom database 3500 detailed pictures 6 grades rot. heterogeneous provided inputs our which was achieve an impressive overall accuracy 94.82%. performance model's robustness also using multitude measures such as precision, recall, F1 score. proves superior in comparison conventional approaches, evidenced both high increased visibility making decisions. discriminate essential stakeholders who want understand basis assigned severities. goes beyond limits academic institutions implications agriculture. automatically provides accurate estimates leading focused intervention, preventing yield loss, improving resource exploitation. aligns objectives pursuing sustainable knowledge-based

Language: Английский

---