Related Experiment Video
Updated: Sep 29, 2025
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
1.8K
Two-Stage Detection Algorithm for Kiwifruit Leaf Diseases Based on Deep Learning.
Jia Yao1,2, Yubo Wang1,2, Ying Xiang1,2
1College of Information Engineering, Sichuan Agricultural University, Ya'an 625000, China.
Plants (Basel, Switzerland)
|March 26, 2022
Summary
This study introduces a novel deep learning approach for identifying kiwifruit diseases, achieving 96.6% accuracy. The method effectively segments diseased leaves from complex backgrounds, aiding in precise crop monitoring.
Area of Science:
- Agricultural Science
- Computer Vision
- Deep Learning
Background:
- Traditional crop disease identification relies on subjective human inspection, leading to inaccuracies.
- Complex natural backgrounds and disease characteristics pose challenges for automated detection.
Purpose of the Study:
- To develop an innovative deep learning method for accurate identification of kiwifruit diseases.
- To overcome limitations of traditional methods and complex environmental factors in disease detection.
Main Methods:
- Utilized deep learning and computer vision models, including YOLOX for target detection and UNet/DeepLabv3+ for semantic segmentation.
- Created the first high-quality kiwifruit disease dataset and employed a learning rate decay training strategy.
- Developed a two-stage disease detection algorithm to isolate leaves and remove background interference.
Main Results:
- Achieved a 96.6% accuracy rate in identifying kiwifruit diseases using the ResNet101 network.
- Demonstrated high accuracy, robustness, and a wide detection range for the proposed algorithm.
- Successfully stripped kiwi leaves from natural backgrounds, mitigating complex environmental influences.
Conclusions:
- The developed two-stage disease detection algorithm offers an efficient solution for precise crop disease monitoring.
- The research provides a robust and accurate method for identifying kiwifruit diseases, improving agricultural management.
- This work establishes a new benchmark for automated crop disease identification using advanced AI techniques.
