An Autonomous Institution

Department of INFORMATION TECHNOLOGY Engineering

21EE02P - PROJECT PHASE REVIEW - ZEROTH / I / II

PLANT DISEASE DETECTION USING LEAF IMAGES ( CNN )

B iotech,

PRESENTED BY
Chemi cal, ECE
& IT

VH13081 Mariappan B - 113023205060 - V Sem

VH13077 Lohith R - 113023205056 - V Sem
VH13080 Maharajan N - 113023205059 - V Sem

Supervisor Head of the Department

Date: 30.08.2025 Mrs.B.Sumathi Mrs.M.Malleeswari
 PROJECT STRUCTURE

The proposed project work consisting of the Chapters as follows.

Chapter 1: Introduction
Chapter 2: Objective
Chapter 3: Literature survey
Chapter 4: Proposed methodology
Chapter 4: Proposed model
Chapter 5: Experiments and Results
Chapter 5: Discussion and Conclusion

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 2
 INTRODUCTION

• Agriculture is a key sector but affected by plant diseases

• Manual disease detection is slow and error-prone

• AI & Computer Vision can analyze leaf images automatically

• Goal: Build an AI system for early and accurate plant disease detection

• Image suggestion: Healthy vs. diseased leaf comparison

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 3
 OBJECTIVE

▪ Build an AI system to detect plant diseases from leaf images

▪ Provide instant disease name and suggested remedy

▪ Support farmers with early, accurate crop health detection

▪ Reduce crop loss and improve agricultural productivity

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 4
 LITERATURE SURVEY TEMPLATE

RESEARCH ARTICLE :01

TITLE OF THE RESEARCH ARTICLE Plant Disease Detection Using Convolutional Neural
Networks (CNNs)
PROBLEM ADDRESSED / IDENTIFIED Traditional methods of disease detection are slow and
inaccurate
AIM / OBJECTIVES To design an automated CNN model to detect and
classify plant diseases from leaf images.
NOVELTY / SIGNIFICANCE CNN removes the need for manual feature extraction,
improving accuracy.
LIMITATION / WEAKNESS Dataset (Plant Village) contains lab images; real-world
images not considered.
FINDINGS / CONCLUSION CNN achieves ~95% accuracy on PlantVillage dataset,
proving AI can automate plant disease detection.
AREAS OF IMPROVEMENT / Adapt CNN for real-field conditions and more crop
FUTURE ENHANCEMENT varieties.

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 5
 PROPOSED METHODOLOGY
(SAMPLE)

➢ Data Collection – PlantVillage / real images

➢ Preprocessing – Resize, Normalize, Augment

➢ Model Training – CNN/Transfer Learning

➢ Classification – Predict Healthy/Disease class

➢ Evaluation – Accuracy, Precision, Recall

➢ Deployment – Mobile/Web application

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 6
 PROPOSED RETRIEVAL MODEL
(SAMPLE)

✓ Input: Leaf Image Preprocessing: Resize → Normalize → Augment

✓ Model: CNN / ResNet / MobileNet

✓ Output: Healthy / Disease Type (e.g., Early Blight, Powdery

Mildew)

✓ Deployment: Mobile app for farmers (instant detection)

✓ Image suggestion: CNN architecture or block diagram

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 7
 EXPERIMENTS AND RESULTS
(SAMPLE)

Fig. 3. Landsat imageries. (a): input query imageries; (b): retrieved imageries

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 8
 DISCUSSION AND CONCLUSION
(SAMPLE)

✓ AI improves speed & accuracy in disease detection

✓ Helps farmers reduce crop losses

✓ System is scalable & cost-effective

✓ Challenges: Background noise, lighting variations in real fields

Future Work:
✓ Support more crops
✓ Develop offline mobile app
✓ Integrate IoT for smart farming

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 9
 REFERENCES
(SAMPLE)

[1] Y. Djenouri, A. Belhadi, A. Yazidi, G. Srivastava, and J. C. Lin, ‘‘Artificial intelligence of

medicalthings for disease detection using ensemble deep learning and attention mechanism,’’
Expert Syst., vol. 41, no. 6, Jun. 2024, Art. no. e13093.

[2] B. Dey, R. Ahmed, J. Ferdous, M. M. U. Haque, R. Khatun, F. E. Hasan, and S. N. Uddin,

‘‘Automated plant species identification from the stomata images using deep neural network: A
study of selected mangrove and freshwater swamp forest tree species of Bangladesh,’’ Ecol.
Informat., vol. 75, Jul. 2023, Art. no. 102128. [Online].

[3] B. Dey, M. M. U. Haque, R. Khatun, and R. Ahmed, ‘‘Comparative performance of four CNN-
based deep learning variants in detecting Hispa pest, two fungal diseases, and NPK deficiency
symptoms of Rice (Oryza sativa),’’ Comput. Electron. Agricult., vol. 202, Nov. 2024,

[4] S. P. Mohanty, D. P. Hughes, and M. Salathé, ‘‘Using deep learning for image-based plant
disease detection,’’ Frontiers Plant Sci., vol. 7, p. 1419, Sep. 2024.

[5] N. Karthikeyan, M. Anjana, . Anusha, R. Divya, and A. Vinod, ‘‘Leaf disease detection using
image processing,’’ Int. J. Innov. Sci. Eng. Technol, vol. 7, pp. 60–65, 2020.

Vel Tech High Tech Dr Rangarajan Dr Sakunthala Engineering College An Autonomous Institution 10
 Thank you