Related Experiment Video
Updated: Oct 30, 2025
06:41
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
Published on: March 28, 2025
1.2K
AI-Driven Framework for Recognition of Guava Plant Diseases through Machine Learning from DSLR Camera Sensor Based
Ahmad Almadhor1, Hafiz Tayyab Rauf2, Muhammad Ikram Ullah Lali3
1Department of Computer Engineering, Networks Jouf University, Sakaka 72388, Saudi Arabia.
Sensors (Basel, Switzerland)
|July 2, 2021
Summary
An artificial intelligence (AI) framework accurately detects common guava plant diseases using image analysis. This AI system achieves 99% accuracy in identifying four fruit diseases, aiding farmers in early detection and preventing crop loss.
Area of Science:
- Agricultural Science
- Computer Science
- Plant Pathology
Background:
- Plant diseases significantly reduce agricultural yield and quality.
- Guava, a vital tropical fruit, is susceptible to numerous fungal, bacterial, and other pathogens.
- Accurate diagnosis of guava diseases is challenging due to subtle symptom variations, leading to potential economic losses.
Purpose of the Study:
- To develop an artificial intelligence (AI) driven framework for automatic detection and classification of common guava plant diseases.
- To improve the accuracy and efficiency of guava disease diagnosis, thereby minimizing economic losses for farmers.
Main Methods:
- Employed AI for image segmentation using ΔE color difference to isolate diseased areas.
- Extracted features using color (RGB, HSV) histograms and textural (LBP) analysis.
- Utilized machine learning classifiers (Fine KNN, Complex Tree, Boosted Tree, Bagged Tree, Cubic SVM) for disease recognition.
Main Results:
- The AI framework achieved high accuracy in detecting guava diseases from high-resolution images.
- The Bagged Tree classifier, combined with RGB, HSV, and LBP features, demonstrated 99% accuracy in identifying four guava fruit diseases (Canker, Mummification, Dot, and Rust) and distinguishing them from healthy fruit.
Conclusions:
- The proposed AI framework offers a reliable solution for automated guava disease detection.
- Early and accurate disease identification can help farmers implement timely interventions, preventing significant production losses and improving crop management.
