Deep Learning Algorithms Correctly Classify Brassica rapa Varieties Using Digital Images

Jung, Minah; Song, Jong Seob; Hong, Seong-Min; Kim, SunWoo; Go, Sangjin; Lim, Yong Pyo; Park, Juhan; Park, Sung Goo; Kim, Yongmin

doi:10.3389/fpls.2021.738685

Cited by 8 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important genomic layer of information is “Bulk-RNASeq,” which can be implemented for accurate data analysis and prediction. ML aims at providing innovative approaches for prediction-based model development; Girma (2019) discussed the ML approach in mungbean to classify the raw quality of samples by analyzing digital imaging data; Jung et al (2021) applied the deep learning algorithm to correctly identify the Brassica napa varieties, followed by a cross-validation approach. Another important microgreen vegetable crop is Broccoli ( Brassica oleracea L. var.…”

Section: Strategies To Overcome Limitations Of Microgreen Productionmentioning

confidence: 99%

Prospects of microgreens as budding living functional food: Breeding and biofortification through OMICS and other approaches for nutritional security

Gupta

Sharma

Singh³

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

Nutrient deficiency has resulted in impaired growth and development of the population globally. Microgreens are considered immature greens (required light for photosynthesis and growing medium) and developed from the seeds of vegetables, legumes, herbs, and cereals. These are considered “living superfood/functional food” due to the presence of chlorophyll, beta carotene, lutein, and minerals like magnesium (Mg), Potassium (K), Phosphorus (P), and Calcium (Ca). Microgreens are rich at the nutritional level and contain several phytoactive compounds (carotenoids, phenols, glucosinolates, polysterols) that are helpful for human health on Earth and in space due to their anti-microbial, anti-inflammatory, antioxidant, and anti-carcinogenic properties. Microgreens can be used as plant-based nutritive vegetarian foods that will be fruitful as a nourishing constituent in the food industryfor garnish purposes, complement flavor, texture, and color to salads, soups, flat-breads, pizzas, and sandwiches (substitute to lettuce in tacos, sandwich, burger). Good handling practices may enhance microgreens’stability, storage, and shelf-life under appropriate conditions, including light, temperature, nutrients, humidity, and substrate. Moreover, the substrate may be a nutritive liquid solution (hydroponic system) or solid medium (coco peat, coconut fiber, coir dust and husks, sand, vermicompost, sugarcane filter cake, etc.) based on a variety of microgreens. However integrated multiomics approaches alongwith nutriomics and foodomics may be explored and utilized to identify and breed most potential microgreen genotypes, biofortify including increasing the nutritional content (macro-elements:K, Ca and Mg; oligo-elements: Fe and Zn and antioxidant activity) and microgreens related other traits viz., fast growth, good nutritional values, high germination percentage, and appropriate shelf-life through the implementation of integrated approaches includes genomics, transcriptomics, sequencing-based approaches, molecular breeding, machine learning, nanoparticles, and seed priming strategiesetc.

show abstract

Section: Strategies To Overcome Limitations Of Microgreen Productionmentioning

confidence: 99%

Prospects of microgreens as budding living functional food: Breeding and biofortification through OMICS and other approaches for nutritional security

Gupta

Sharma

Singh³

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…Embarking on a trajectory that converges horticultural insight with computational acumen, this research embarks on a journey towards the hallowed precincts of early detection in legume crop diseases (Waheed et al, 2020). By harnessing the capacity of CNNs, a form of artificial neural networks meticulously designed for image analysis, we endeavour to forge an avant-garde tool that transcends human sensory constraints (Jung et al, 2021). The core tenet of this endeavour lies in the seamless amalgamation of data-driven prowess and botanical expertise, an interface wherein the digital sentinel augments human cognition.…”

Section: Introductionmentioning

confidence: 99%

Exploring Advanced Machine Learning Techniques for Swift Legume Disease Detection

Cho,

Na,

Koh

2024

View full text Add to dashboard Cite

Background: In the realm of agriculture, the insidious menace of legume crop diseases looms large, posing a significant threat to food security. This study embarks on a transformative journey, harnessing the prowess of Convolutional Neural Networks (CNNs), to fortify early disease detection in legume crops. By utilizing the inherent capabilities of deep learning, try to develop a sentinel that can identify even the most minor signs of crop diseases. Thorough data curation and preprocessing provide the system the ability to examine photos of legume leaves with previously unheard-of clarity. Methods: Meticulously crafted, the CNN architecture plays the role of a virtuoso, skilfully traversing the convolutional layers. It gains proficiency in the complex language of illness-induced aberrations via intense training, enabling it to discern between health and illness. Result: Provide remarkable results from the experimental experience using a wide range of assessment metrics. By undertaking this project, the commitment to preserving agricultural yields and, consequently, global food security is reaffirmed. It portends a more optimistic future for legume farming by indicating a ground-breaking effort at the nexus of artificial intelligence and agriculture.

show abstract

“…In recent years, deep learning ( 6 ) has created a research boom in various fields. In the agricultural field, deep learning combined with machine vision has been widely used in plant recognition and detection, such as recognition of wood categories ( 7 ), fruit and vegetable classification ( 8–10 ), plant pest and disease identification ( 11 , 12 ), crop yield estimation ( 13 , 14 ) and weed detection ( 15 ).…”

Section: Introductionmentioning

confidence: 99%

Dried shiitake mushroom grade recognition using D-VGG network and machine vision

Wang,

Dong,

Wang

et al. 2023

Front. Nutr.

View full text Add to dashboard Cite

Grading dried shiitake mushrooms is an indispensable production step, as there are large quality differences between different grades, which affect the product’s price and marketability. Dried shiitake mushroom samples have irregular shapes, small morphological differences between different grades of the same species, and they may occur in mixed grades, which causes challenges to the automatic grade recognition using machine vision. In this study, a comprehensive method to solve this problem is provided, including image acquisition, preprocessing, dataset creation, and grade recognition. The osprey optimization algorithm (OOA) is used to improve the computational efficiency of Otsu’s threshold binarization and obtain complete mushroom contours samples efficiently. Then, a method for dried shiitake mushroom grade recognition based on the improved VGG network (D-VGG) is proposed. The method uses the VGG16 network as the base framework, optimizes the convolutional layer of the network, and uses a global average pooling layer instead of a fully connected layer to reduce the risk of model overfitting. In addition, a residual module and batch normalization are introduced to enhance the learning effect of texture details, accelerate the convergence of the model, and improve the stability of the training process. An improved channel attention network is proposed to enhance the feature weights of different channels and improve the grading performance of the model. The experimental results show that the improved network model (D-VGG) can recognize different dried shiitake mushroom grades with high accuracy and recognition efficiency, achieving a final grading accuracy of 96.21%, with only 46.77 ms required to process a single image. The dried shiitake mushroom grade recognition method proposed in this study provides a new implementation approach for the dried shiitake mushroom quality grading process, as well as a reference for real-time grade recognition of other agricultural products.

show abstract

Deep Learning Algorithms Correctly Classify Brassica rapa Varieties Using Digital Images

Cited by 8 publications

References 36 publications

Prospects of microgreens as budding living functional food: Breeding and biofortification through OMICS and other approaches for nutritional security

Prospects of microgreens as budding living functional food: Breeding and biofortification through OMICS and other approaches for nutritional security

Exploring Advanced Machine Learning Techniques for Swift Legume Disease Detection

Dried shiitake mushroom grade recognition using D-VGG network and machine vision

Contact Info

Product

Resources

About