01 Source Code Only
₹99
One-time Payment
- Complete project source code
- Database / data resources
- Dependencies & configuration
- README / setup guide
- Instant download access
MACHINE-LEARNING Project
Skin Disease Detection Final Year Project Source Code
Complete final-year project source code with frontend, backend, database and setup documentation. Instant download after secure payment.
Hover to zoom · Click to expand
Choose the Package That Fits You Best
Simple pricing. Instant access. Secure checkout.
02 Code + Setup Support
₹248
One-time Payment
- Everything in Source Code plan
- Remote setup assistance
- Database & configuration setup
- Run verification
- Help via WhatsApp / Email
Project's Overview
DermaSense is a final year project built with Python Flask, TensorFlow/Keras, and SQLite for students who want a machine learning based healthcare web application. This final year project allows users to upload skin images, run CNN inference, view predicted disease labels with confidence scores, and maintain private prediction history. The system also supports disease information, precautions, medicine suggestions, optional Grad-CAM overlays, printable reports, and user profile management. The admin console of this final year project includes user management, prediction logs, disease catalog management, precautions, medicines, model upload, model activation, monitoring, and maintenance tools. With support for .keras and .h5 models, DermNet-style class labels, and a demo model generator, DermaSense is suitable for a final year major project in machine learning, Flask, TensorFlow, image processing, or healthcare AI.
Login Credentials
Demo User
- Username:
demo_user - Password:
UserPass123 - URL:
/auth/login
Administrator
- Username:
admin - Password:
AdminPass123 - URL:
/auth/admin/login
- Separate admin login for this final year project with distinct admin session
- Admin dashboard with aggregate stats, recent predictions, and activity-style feed
- User list, search, view, and delete features
- Global prediction and uploaded image log
- Disease CRUD with class order screen for model index alignment
- Precaution and medicine suggestion CRUD per disease
- Model management for
.kerasand.h5uploads - Optional class label JSON upload or pasted JSON support
- Input preprocessing mode selection:
pixel255orunit - Model validation before activation
- Disease histograms and recent monitoring logs
- Per-user activity summaries
- Bulk clear tools for demo maintenance
- Admin profile and password update
- User registration and login in this final year project with email or username
- Dashboard with welcome section, analysis counts, metrics, and recent predictions
- Profile update for name, email, username, phone, organization, and country
- Password change support
- Skin image upload with JPG/JPEG/PNG validation
- Image upload size limit support
- CNN inference using active TensorFlow/Keras model
- Prediction result with disease label and confidence score
- Disease precautions and medicine suggestions where available
- Optional cause and treatment information
- Optional Grad-CAM heatmap image
- Case title and private notes
- Prediction history with search and filter
- Delete own predictions with confirmation
- Printable HTML report and download support
- Access control so users only see their own records
- SQLite database used by default in this final year project
- Optional
DATABASE_URLoverride for another database - Lightweight SQLite migrations for existing databases
- Supports pretrained
model.h5workflow - Supports
.kerasdemo model generation usingcreate_model.py - 24-class DermNet-style class label workflow
dermnet_class_labels.jsonsupport for correct model output mapping- Optional Indonesian clinical blurbs import using
scripts/import_dermnet_catalog.py - Optional OpenCV Grad-CAM support
- Optional HDF5 support through
h5py - Seed script for demo user and admin accounts
- Suitable for final year project demo, viva, source code review, and report preparation
- Educational decision-support disclaimer included
- Open the final year project folder in terminal:
cd "path/to/Skin Disease Detection using machine learning and tensorflow" - Create and activate a virtual environment:
python -m venv .venv
Windows:.venv\Scripts\activate
Linux/macOS:source .venv/bin/activate - Install dependencies:
pip install -r requirements.txt - Optional: initialize demo data and model:
python seed.py
python create_model.py - Optional: import DermNet catalog information:
python scripts/import_dermnet_catalog.py - Start the final year Flask TensorFlow project:
python run.py - Open the app at:
http://127.0.0.1:5000/ - Recommended model activation path:
- Login as admin
- Go to Admin → Model
- Upload
model.h5 - Attach
dermnet_class_labels.json - Choose “Scale to 0–1 (divide by 255)”
- Submit “Validate & activate”
README Included
Setup Support Available
Demo User
- Username:
demo_user - Password:
UserPass123 - URL:
/auth/login
Administrator
- Username:
admin - Password:
AdminPass123 - URL:
/auth/admin/login