Related Experiment Video
Updated: Aug 20, 2025
06:28
Author Spotlight: Unraveling Plant Responses to Abiotic Stresses Using the PlantScreen Robotic Platform
Published on: June 7, 2024
1.9K
Applications of Computer Vision on Automatic Potato Plant Disease Detection: A Systematic Literature Review
Natnael Tilahun Sinshaw1, Beakal Gizachew Assefa2, Sudhir Kumar Mohapatra3
1Department of Software Engineering, CoE for HPC and BDA, AASTU, Addis Ababa, Ethiopia.
Computational Intelligence and Neuroscience
|November 24, 2022
Summary
This review highlights AI-driven methods for detecting major potato diseases like late blight and bacterial wilt, crucial for agriculture in developing nations. Deep learning models show superior performance over traditional machine learning for accurate crop disease identification.
Area of Science:
- Agricultural Science
- Computer Science
- Artificial Intelligence
Background:
- Agriculture is vital to developing economies, but crop diseases significantly reduce yield.
- Traditional plant disease detection methods are inefficient and prone to bias.
- Potato crops are particularly vulnerable to diseases, impacting food security.
Approach:
- A systematic literature review was conducted on 39 primary studies.
- Focus on computer vision and machine learning techniques for potato disease identification.
- Surveyed various machine learning algorithms applied in crop disease detection.
Key Points:
- Identified late blight, early blight, and bacterial wilt as the most prevalent potato diseases.
- Deep learning algorithms are more commonly utilized than classical machine learning for crop disease detection.
- The review categorizes current state-of-the-art algorithms in the field.
Conclusions:
- AI and machine learning offer advanced solutions for timely and accurate potato disease detection.
- Deep learning demonstrates significant potential in improving crop yield and agricultural productivity.
- Identified open research challenges and future directions in AI-based plant disease management.
