Plant diseases and pests detection based on deep learning: a review

Area of Science:

• Agricultural Science
• Computer Science
• Image Processing

Background:

• Plant diseases and pests critically impact crop yield and quality.
• Digital image processing offers a method for plant disease and pest identification.
• Deep learning has emerged as a superior alternative to traditional identification methods.

Purpose of the Study:

• To review deep learning applications in plant disease and pest detection.
• To compare deep learning with traditional detection methods.
• To analyze future trends and challenges in this field.

Main Methods:

• Categorization of deep learning methods into classification, detection, and segmentation networks.
• Summary of advantages and disadvantages for each network type.
• Introduction and comparison of common datasets used in studies.

Main Results:

• Deep learning methods show significant advancements over traditional approaches.
• Classification, detection, and segmentation networks offer distinct capabilities for plant disease identification.
• Performance comparison of existing studies highlights the effectiveness of deep learning.

Conclusions:

• Deep learning-based plant disease and pest detection presents a promising research area.
• Practical application challenges exist but can be addressed with proposed solutions.
• Future research should focus on advancing deep learning techniques for robust crop monitoring.