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
Black-and-White Photo Colourisation
Adds plausible colour to old black-and-white photos with a GAN
3-4 weeks build
Overview
Photos are converted to Lab colour space so the network only has to predict the two colour channels from lightness. A pix2pix-style GAN with a pretrained ResNet encoder is trained on a subset of COCO, and its results are compared with a plain regression model to show why adversarial training avoids washed-out, sepia-looking output.
What makes it stand up
- 01Lab colour space formulation that predicts only the ab channels
- 02U-Net generator with a pretrained ResNet encoder
- 03L1-only baseline compared against the adversarial model
- 04Batch colourisation of scanned family photos
- 05Colourfulness score and a small user preference study in the report
Module breakdown
- 01
Colour pipeline
RGB to Lab conversion and reconstruction utilities.
- 02
Baseline
Regression model trained with L1 loss alone.
- 03
GAN
Conditional generator and PatchGAN discriminator.
- 04
Training
Encoder pretraining followed by adversarial fine-tuning.
- 05
App
Streamlit upload with side-by-side and batch download.
After this, you will be able to
- Explain why colourisation is framed in Lab rather than RGB
- Defend why adversarial loss gives more vivid colours than L1 alone
- Demo colourising a photo from a family album
Technology stack
- Python
- PyTorch
- OpenCV
- scikit-image
- Streamlit
- 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