PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Major Project
Sign Language Recognition
Real-time ISL fingerspelling to text from a webcam
3-4 weeks build
Overview
Indian Sign Language fingerspelling recognised live from a webcam. MediaPipe extracts hand landmarks, a compact classifier maps them to letters, and a word-assembly layer with temporal smoothing turns a stream of predictions into readable text without flickering between characters.
What makes it stand up
- 01Landmark-based, so it works in varied lighting and backgrounds
- 02Temporal smoothing that stops single-frame misreads
- 03Word assembly with a hold-to-commit gesture
- 04Training notebook plus the collected landmark dataset
- 05Runs on a laptop CPU — no GPU needed for the demo
Module breakdown
- 01
Capture
Webcam pipeline and hand landmark extraction.
- 02
Classifier
Model training, validation and confusion analysis.
- 03
Smoothing
Temporal voting across a sliding window.
- 04
Assembly
Letters into words, with space and delete gestures.
- 05
Interface
Live preview, confidence bars and text output.
After this, you will be able to
- Explain why landmarks generalise better than raw pixels here
- Demo it live in the exam hall's lighting
- Discuss the accessibility impact and the dataset's limits
Technology stack
- Python
- MediaPipe
- TensorFlow
- OpenCV
- Streamlit
- Level
- Major Project
- Domain
- Machine Learning
- Build time
- 3-4 weeks
- Difficulty
- Rating
- 4.8 / 5 · 147
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