Assessfy Pvt. Ltd Moderate 7 milestones 50 marks

A Model for Prediction of Tomato Crop Disease Using CNN

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

A Model for Prediction of Tomato Crop Disease Using CNN

Objective: Develop a deep learning model to accurately predict tomato crop diseases from leaf images.

Context: Tomato farmers in India face significant losses due to late or incorrect identification of crop diseases, impacting food security and livelihoods. Early, automated detection can help optimize interventions and reduce pesticide misuse.

What you'll build: You'll create a convolutional neural network (CNN) using Python and frameworks like TensorFlow or PyTorch to classify healthy and diseased tomato leaves. The project involves data collection, preprocessing with OpenCV and NumPy, data augmentation, model training, and evaluation using accuracy metrics and confusion matrices, all documented in Jupyter Notebooks or Google Colab.

Deliverables: Working image classification model, codebase, evaluation report with accuracy and confusion matrix, and a demonstration notebook.

Milestones

No deliverable is required for this milestone.

2. Data collection (disease vs. healthy images)

5 marks 5d

Collect and submit a labeled dataset of tomato leaf images, ensuring clear separation between disease-affected and healthy samples. Include at least two disease categories and healthy leaves, with a minimum of 200 images per class. Provide a CSV or folder structure showing labels and image sources for verification.

3. Data preprocessing and augmentation

5 marks 5d

Preprocess the collected images by resizing, normalizing pixel values, and organizing them into training, validation, and test sets. Apply at least two augmentation techniques (e.g., rotation, flipping) to increase dataset diversity. Submit your preprocessing code, a summary table of image counts per class, and sample augmented images for review.

4. CNN architecture design

5 marks 5d

Design and implement a CNN model tailored for tomato disease classification, specifying all layers, activation functions, and output structure. Submit your model architecture code and a diagram or summary table of the network layers. Ensure the model input matches your preprocessed image dimensions and output matches the number of classes.

5. Training, testing, and hyperparameter tuning

5 marks 5d

Train your CNN using the prepared dataset, documenting the training/validation accuracy and loss over epochs. Experiment with at least two hyperparameters (e.g., learning rate, batch size) and report their effects. Submit your training code, plots of accuracy/loss curves, and a brief summary of tuning results.

6. Accuracy evaluation and confusion matrix

15 marks 5d

Evaluate your trained model on the test set, reporting overall accuracy and a confusion matrix distinguishing each disease and healthy class. Submit the evaluation code, the confusion matrix plot, and a short interpretation of misclassifications. Ensure your results are reproducible with provided code and test data.

7. Deployment plan (mobile/web app optional)

15 marks 5d

Draft a deployment plan describing how your trained model could be integrated into a mobile or web application for real-time tomato disease prediction. Outline the technical steps, required tools, and user workflow. Submit a written plan (1-2 pages) and, if applicable, a prototype or code snippet demonstrating model inference in the chosen environment.

Open internships using this project -->

Upcoming sessions

Session	Window	Enrolled
A Model for Prediction of Tomato Crop Disease Using CNN	11 Jun 2026 to 10 Jun 2028	0

Skills you'll learn

Deep Learning (CNNs)Image ClassificationPython ProgrammingData AugmentationModel Evaluation (AccuracyConfusion Matrix)

Tools used

Python (TensorFlow/Keras or PyTorch) OpenCVNumPyMatplotlib Jupyter Notebooks or Google Colab PlantVillage or similar datasets

Prerequisites

Basics of Deep Learning and CNN architecture Python programming Understanding of image datasets and annotation

Available mentors

Priyang Kumar

Free

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

A Model for Prediction of Tomato Crop Disease Using CNN

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Moderate

A Model for Prediction of Tomato Crop…

Assessfy

Auto-issued on completion One-click LinkedIn add