Assessfy Pvt. Ltd Moderate 5 milestones 100 marks

Image-Based Crop Disease Detection for Indian Farmers

Target year: TE Sem 5-6 (Mini-Project-IIA/IIB) AICTE: 3 credits · ~75 hrs Bloom: Analyze MU CBCS: AI601/AI701 Mini-Project 2A/2B

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

Train a CNN classifier on the PlantVillage dataset extended with images of Indian crops (rice, wheat, sugarcane, cotton) showing healthy + 5 common diseases each. Deploy via a mobile-friendly Flask web app where a farmer uploads a leaf photo and gets disease + treatment suggestion. Support Marathi + Hindi UI.

Course Learning Outcomes (CLOs):
CLO1: Apply transfer learning to a domain dataset.
CLO2: Build a balanced augmentation pipeline for class imbalance.
CLO3: Achieve >85% accuracy on held-out test set.
CLO4: Design a multilingual, low-bandwidth-friendly mobile web UI.
CLO5: Communicate ML-system impact to non-technical stakeholders (farmers).

Industry/societal relevance: Indian agritech (DeHaat, Cropin, BharatAgri) hire CV engineers; aligns with PM-KISAN and digital-agriculture mission.

Milestones

1. Data Collection + Curation

15 marks 10d

Combine PlantVillage + scrape Indian crop disease images (or partner with a krishi college). 4 crops × 6 classes × 200+ imgs.

2. Transfer Learning Baseline

20 marks 12d

Fine-tune ResNet-50 pretrained on ImageNet. Train/val/test split. Report accuracy + per-class F1.

3. Augmentation + Robustness

25 marks 14d

Add rotation, brightness jitter, MixUp. Test on phone-captured (in-the-wild) images. Report drop in accuracy.

4. Flask Web App + Multilingual

20 marks 18d

Upload photo → prediction + Marathi/Hindi/English treatment advice. Responsive Bootstrap UI.

5. Field Validation + Report

20 marks 11d

Test with 5 real farmer-collected images per crop. Document confusion matrix + UX feedback. 8-page report.

Open internships using this project -->

Skills you'll learn

Computer VisionTransfer Learning (ResNet50 / EfficientNet)Image AugmentationMulti-language UI (i18n)Mobile-responsive web designDomain knowledge of crops

Tools used

Python 3.11PyTorch + torchvisionPlantVillage dataset + custom Indian crop datasetFlaskBootstrap 5GitHub

Prerequisites

Intro ML; Python intermediate; basic deep learning (CNNs); web fundamentals

Available mentors

No mentors have signed up for this project yet.

Be the first to mentor

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

Image-Based Crop Disease Detection for Indian Farmers

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

Image-Based Crop Disease Detection fo…

Assessfy

Auto-issued on completion One-click LinkedIn add