Artificial Cognition for Early Leaf Disease Detection using Vision Transformers

Thai, Huy-Tan; Tran-Van, Nhu-Y; Le, Kim-Hung

doi:10.1109/atc52653.2021.9598303

Cited by 50 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…El primer algoritmo se basa en el uso de un recurso tecnológico (robot) que permita la movilidad dentro de la finca con el fin de adquirir datos y una red neuronal para el monitoreo de la roya. Esto basado en el monitoreo los cultivos por medio de un robot como el utilizado por Wijanarko A. et al (2021) [15] y la aplicación de redes neuronales de detección de plagas como lo propone Thai et al, (2021) [75].…”

Section: Resultsunclassified

Proposed Open Systems Model and Intelligent Agriculture in Coffee Farms within the Harvesting Process

Ordonez-Avila¹,

Martínez-Rangel²

2022

Proceedings of the 2nd LACCEI International Multiconference on Entrepreneurship, Innovation and Regional Development (LEIRD 202

View full text Add to dashboard Cite

The countries that produce the most coffee worldwide have an economy based on agribusiness and it is noteworthy that some of them apply various methods based on Industry 4.0 in their processes. However, in coffee production these technologies have a very limited application. The use of open systems makes it possible to talk about intelligent agriculture, which implements various technologies to improve some processes. This research work identifies the different technologies of Industry 4.0 that could be used in agriculture by the leading countries in coffee production as proposed in this research work. The development of the theoretical and methodological framework allows identifying three general steps in the management of information in this area: generation, grouping and visualization. After the theoretical review, the main trends of these countries with signs of intelligent agriculture are presented as results, given that they apply Industry 4.0 technologies. To visualize the impact that these technologies can have on coffee farms, the open systems model of Katz & Kan is proposed. The application of this model will allow the integration of Industry 4.0 within coffee farms. Finally, it is concluded that the most used technology is the internet of things and sensors, which many of the authors used together, while robotics is the least implemented. By implementing these technologies, the authors showed benefits in crop monitoring, irrigation systems and management systems.

show abstract

Section: Resultsunclassified

Proposed Open Systems Model and Intelligent Agriculture in Coffee Farms within the Harvesting Process

Ordonez-Avila¹,

Martínez-Rangel²

2022

Proceedings of the 2nd LACCEI International Multiconference on Entrepreneurship, Innovation and Regional Development (LEIRD 202

View full text Add to dashboard Cite

show abstract

“…In [151], the authors summarized the results of the challenger VisDrone-DET2021 in which the proponents used different transformers, such as Scaled-YOLOv4 with transformer and BiFPN (SOLOER), Swin-transformer (Swin-T), stronger visual information for tiny object detection (VistrongerDet), and EfficientDet for object detection in the drone imagery. Thai et al [152] demonstrated the use of ViT for cassava leaf disease classification and achieved better performance than did the CNNs. A detailed summary of the existing ViTs for drone imagery data is presented in Table 7.…”

Section: Vits and Drone Imagerymentioning

confidence: 99%

A Comprehensive Survey of Transformers for Computer Vision

Jamil

Piran

Kwon

2023

Drones

View full text Add to dashboard Cite

As a special type of transformer, vision transformers (ViTs) can be used for various computer vision (CV) applications. Convolutional neural networks (CNNs) have several potential problems that can be resolved with ViTs. For image coding tasks such as compression, super-resolution, segmentation, and denoising, different variants of ViTs are used. In our survey, we determined the many CV applications to which ViTs are applicable. CV applications reviewed included image classification, object detection, image segmentation, image compression, image super-resolution, image denoising, anomaly detection, and drone imagery. We reviewed the state of the-art and compiled a list of available models and discussed the pros and cons of each model.

show abstract

“…Furthermore, by employing the Vision Transformer, researchers achieved a minimum of 1% higher accuracy in classifying cassava leaf diseases than wellknown CNN models. They also effectively implemented this model on the Raspberry Pi 4, an edge device, showcasing the substantial potential for its application in the realm of smart agriculture [17]. To the best of our knowledge, only [19] has performed durian disease detection using deep learning approach.…”

Section: Related Workmentioning

confidence: 99%

Durian Disease Classification using Vision Transformer for Cutting-Edge Disease Control

Daud,

Abualqumssan,

Rashid

et al. 2023

IJACSA

View full text Add to dashboard Cite

The durian fruit holds a prominent position as a beloved fruit not only in ASEAN countries but also in European nations. Its significant potential for contributing to economic growth in the agricultural sector is undeniable. However, the prevalence of durian leaf diseases in various ASEAN countries, including Malaysia, Indonesia, the Philippines, and Thailand, presents formidable challenges. Traditionally, the identification of these leaf diseases has relied on manual visual inspection, a laborious and time-consuming process. In response to this challenge, an innovative approach is presented for the classification and recognition of durian leaf diseases, delves into cutting-edge disease control strategies using vision transformer. The diseases include the classes of leaf spot, blight sport, algal leaf spot and healthy class. Our methodology incorporates the utilization of well-established deep learning models, specifically vision transformer model, with meticulous fine-tuning of hyperparameters such as epochs, optimizers, and maximum learning rates. Notably, our research demonstrates an outstanding achievement: vision transformer attains an impressive accuracy rate of 94.12% through the hyperparameter of the Adam optimizer with a maximum learning rate of 0.001. This work not only provides a robust solution for durian disease control but also showcases the potential of advanced deep learning techniques in agricultural practices. Our work contributes to the broader field of precision agriculture and underscores the critical role of technology in securing the future of durian farming.

show abstract

Artificial Cognition for Early Leaf Disease Detection using Vision Transformers

Cited by 50 publications

References 21 publications

Proposed Open Systems Model and Intelligent Agriculture in Coffee Farms within the Harvesting Process

Proposed Open Systems Model and Intelligent Agriculture in Coffee Farms within the Harvesting Process

A Comprehensive Survey of Transformers for Computer Vision

Durian Disease Classification using Vision Transformer for Cutting-Edge Disease Control

Contact Info

Product

Resources

About