PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Signature Verification with CNN & Ensemble Learning
Tells genuine signatures from skilled forgeries using CNN features
3-4 weeks build
Overview
Scanned signatures are cleaned, binarised and size-normalised, then a CNN turns each one into a feature vector. Random forest, SVM and gradient-boosted classifiers vote on whether the sample is genuine or forged, and the report compares each model against the ensemble on the public CEDAR signature set with writer-independent splits.
What makes it stand up
- 01Preprocessing pipeline for noise removal, binarisation and cropping
- 02CNN feature extractor trained on genuine and forged pairs
- 03Soft-voting ensemble of SVM, random forest and XGBoost-style boosting
- 04Writer-independent evaluation so the model is tested on unseen signers
- 05Web upload that returns a verdict with a confidence score
Module breakdown
- 01
Preprocessing
Otsu thresholding, skeleton-safe denoising and aspect-preserving resize.
- 02
Feature extraction
CNN embeddings taken from the penultimate layer.
- 03
Ensemble
Three classifiers combined by soft voting with tuned weights.
- 04
Verification app
Flask page to upload a reference and a query signature.
- 05
Evaluation
FAR, FRR, equal error rate and ROC curves in the report.
After this, you will be able to
- Explain why an ensemble is more robust than a single classifier here
- Defend the difference between writer-dependent and writer-independent testing
- Demo a live verdict on a signature you sign in the viva room
Technology stack
- Python
- TensorFlow
- OpenCV
- scikit-learn
- Flask
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support