EUVIMEDEUVIMED entdecken
Crossref

Identification of Fruit Severity and Disease Detection using Deep Learning Frameworks

Parmar, Prakash J, Shrimali, Mukesh

International Journal of Intelligent Systems and Applications in Engineering · 01.01.2024

DOI: 10.13140/rg.2.2.21286.95049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems and Applications in Engineering, erschienen am 01.01.2024. Verfasst von Parmar und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fruit disease identification is facilitated by the use of Artificial Intelligence (AI) methods in the agricultural sector. Early illness prediction helps in taking the right management measures. This is a significant development in the fight against sickness and the production of high-quality goods to satisfy the world's need. At this point, we may take preventative measures to limit the spread of illness in plants, and the results from those plants will ultimately benefit the expanding human population. Many fruit datasets are accessible for study of plant stems and roots in the public domain. This information may be used effectively even by those without a strong background in agriculture. This study introduces nine new Convolutional Neural Network models for image-based plant leaf classification, including a deep convolutional neural network and eight previously developed models. Two methods of data augmentation are used to the collection of fruit disease images in order to increase its size and depth. There are three distinct color augmentation methods and six distinct position augmentation methods that may be used to enhance the data. These augmentation methods even out the size of each class in the dataset and boost its overall performance. This paper we proposed a fruit disease detection and classification using deep learning model. Six different deep learning frameworks are used such as RESNET50-V2, INCEPTION-V3, MOBILENET-V2, INCEPTION-RESNET-V2, XCEPTION, MOBILENET and VGG-16 for identification fruit diseases. The VGG-16 obtains higher accuracy over other deep learning models as 96.10%. In entire experimental analysis the VGG-16 outperforms higher accuracy than over all deep learning algorithms.

Schlagwörter

fruit disease detectionplant disease diagnosisfruit quality assessment

Zitieren

APA

Parmar, J, P., Shrimali, & Mukesh (2024). Identification of Fruit Severity and Disease Detection using Deep Learning Frameworks. International Journal of Intelligent Systems and Applications in Engineering. https://doi.org/10.13140/rg.2.2.21286.95049

Vancouver

Parmar, J P, Shrimali, Mukesh. Identification of Fruit Severity and Disease Detection using Deep Learning Frameworks. International Journal of Intelligent Systems and Applications in Engineering. 2024. doi:10.13140/rg.2.2.21286.95049

BibTeX
@article{Parmar2024,
  author = {Parmar and J, Prakash and Shrimali and Mukesh},
  title = {Identification of Fruit Severity and Disease Detection using Deep Learning Frameworks},
  journal = {International Journal of Intelligent Systems and Applications in Engineering},
  year = {2024},
  doi = {10.13140/rg.2.2.21286.95049}
}
Kostenlos starten →