Scholarlink

Onion, which is also called as Allium Cepa, is cultivated over an area of 5.7 million ha (Mha) which represents a production of 106.59 million ton (MT) in the world. Onion is a temperate crop but can be grown under a wide range of climatic conditions such as temperate, tropical, and subtropical climate. The best performance can be obtained in mild weather without the extremes of cold and heat and excessive rainfall (Vikaspedia. https://vikaspedia.in/agriculture/crop-production , [1]). As agricultural production increases, there is often a corresponding rise in the incidence of crop diseases, which can significantly impact yield quality and quantity. Early detection of crop diseases is crucial, as it enables farmers to apply the appropriate fertilizers and remedies, thereby preserving the current crop and optimizing resource use. This proposed solution leverages machine learning techniques for identifying diseases in onion crop leaves through image classification. The dataset utilized for this research has been sourced from Karnataka, ensuring region-specific applicability and relevance (Aishwarya and Reddy in Data Brief 54, 2024, [2]). The paper proposed the use of a deep learning model such as DenseNet, Inception, and Convolutional Neural Networks (CNNs) for image classification. All the deep learning models such as DenseNet, Inception, and CNN have shown a good accuracy percentage as 96%, 97%, and 95%, respectively.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Onion Crop Disease Identification Using Deep Learning Models: A Machine Learning Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Madhavi Amondkar,
  • Basant Tiwari

摘要

Onion, which is also called as Allium Cepa, is cultivated over an area of 5.7 million ha (Mha) which represents a production of 106.59 million ton (MT) in the world. Onion is a temperate crop but can be grown under a wide range of climatic conditions such as temperate, tropical, and subtropical climate. The best performance can be obtained in mild weather without the extremes of cold and heat and excessive rainfall (Vikaspedia. https://vikaspedia.in/agriculture/crop-production , [1]). As agricultural production increases, there is often a corresponding rise in the incidence of crop diseases, which can significantly impact yield quality and quantity. Early detection of crop diseases is crucial, as it enables farmers to apply the appropriate fertilizers and remedies, thereby preserving the current crop and optimizing resource use. This proposed solution leverages machine learning techniques for identifying diseases in onion crop leaves through image classification. The dataset utilized for this research has been sourced from Karnataka, ensuring region-specific applicability and relevance (Aishwarya and Reddy in Data Brief 54, 2024, [2]). The paper proposed the use of a deep learning model such as DenseNet, Inception, and Convolutional Neural Networks (CNNs) for image classification. All the deep learning models such as DenseNet, Inception, and CNN have shown a good accuracy percentage as 96%, 97%, and 95%, respectively.