Scribd
Upload
4 views6 pages

IoT-Based Rice Disease Detection System

The document presents a UG project on an IoT-based system for early detection of crop diseases, specifically targeting rice plants using image processing and machine learning with a focus on SVM for classification. The project has achieved a 72.93% accuracy in disease detection, with plans for future enhancements including broader disease coverage and real-time monitoring capabilities. The methodology includes feature extraction from images and model validation through performance metrics.

Uploaded by

21ELB370MOHAMMAD AREEB HASAN KHAN
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views6 pages

IoT-Based Rice Disease Detection System

The document presents a UG project on an IoT-based system for early detection of crop diseases, specifically targeting rice plants using image processing and machine learning with a focus on SVM for classification. The project has achieved a 72.93% accuracy in disease detection, with plans for future enhancements including broader disease coverage and real-time monitoring capabilities. The methodology includes feature extraction from images and model validation through performance metrics.

Uploaded by

21ELB370MOHAMMAD AREEB HASAN KHAN
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd

Department of Electronics Engineering, AMU

Presentation of UG Project (Phase II)


IOT based early detection
system for crop diseases.

Name of student 1: _Mohd Areeb Hasan Khan_ Faculty No.: _21ELB370_, Enrolment No.:_GM6684_
Name of student 2: _ Mohammad Shiraz _ Faculty No.: _21ELB217 _ , Enrolment No.:_GM6564 _

Date of Presentation: 01.03.2025


Abstract
•Objective:
•Develop an automated system for detecting rice plant diseases using
image processing and machine learning.
•Utilize SVM (Support Vector Machine) for accurate disease
classification.
•Methodology:
•Extract key features (HSV and GLCM) from rice plant images.
•Train a multi-class SVM model using fitcecoc for disease classification.
•Validate the model using a confusion matrix and performance metrics.
•Progress:
•Completed dataset collection and preprocessing.
•Worked on Edge detection.
•Implemented feature extraction and SVM training.
•Achieved initial testing with promising results.
Slide: 2 of 6
System Workflow
Start 1. Load Pre-trained Model
- Pre-trained SVM model for classification.
Load Pre-Trained
SVM model - Trained on HSV and GLCM features.
2. Select and Preprocess Image
Processing Image (Resize, Enhance contrast, Convert to HSV) - Image selected and preprocessed.
- Resize, grayscale, and filter.
Extract Features(HSV, GLCM) 3. Extract Features
- HSV: Mean Hue, Saturation, Value.
Predict Disease using SVM Model - GLCM: Contrast, Correlation, Energy, Homogeneity.
4. Predict Disease
Display Image - SVM model predicts disease class.
5. Display Results
Show Result
(Disease Detected:) - Show image and predicted disease.
6. End
End - Process complete.
Slide: 3 of 6
Results and Performance
evalution
Accuracy: 72.93%
F1 Score for Brown spot: 65.29%
F1 Score for healthy: 78.06%
F1 Score for Leaf scald: 73.88%

Slide: 4 of 6
Conclusion
The current model achieves an overall accuracy of 72.93%, with strong performance
on leaf scald but challenges in distinguishing brown spot.

Future Enhancements:

• Expand the model to include additional diseases for broader applicability.

• Improve accuracy through advanced feature extraction, data augmentation, and


hyperparameter tuning.

• Integrate a hardware communication system using ESP32 for real-time disease


detection and monitoring in the field.

These upgrades will make the system more robust, scalable, and practical for real-
world agricultural applications.
Slide: 5 5of 6
References
1. N. Kitpo and M. Inoue, "Early Rice Disease Detection and Position Mapping System
Using Drone and IoT Architecture," 2018 12th South East Asian Technical University
Consortium Symposium (SEATUC), Yogyakarta, Indonesia, 2018, pp. 1-6.
doi:10.1109/SEATUC.2018.8788764.
2. K. S. Amit, A. Rubiya, and R. B. Senthil, “Classification of Rice Disease using Digital
Image Processing and SVM Classifier,” International Journal of Electrical and
Electronics Engineers (IJEEE), vol. 7, 2015.
3. M. I. Pavel, S. M. Kamruzzaman, S. S. Hasan, and S. R. Sabuj, "An IoT-based plant health
monitoring system implementing image processing," 2019 IEEE 4th International
Conference on Computer and Communication Systems (ICCCS), Dhaka, Bangladesh,
2019, pp. 206-210, doi: 10.1109/ICCCS.2019.00047.

Slide: 6 6of 6

You might also like