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
Structural Crack Detection
Finds and outlines cracks in concrete and wall images
2-3 weeks build
Overview
A two-stage inspection tool: a CNN classifies image patches as cracked or intact, trained on public datasets such as SDNET2018, then a U-Net segments the crack pixels so its length and width can be estimated. Inspectors upload wall or slab photos and get an annotated image with a severity grade, useful for prioritising which surfaces need a closer look.
What makes it stand up
- 01Patch classifier trained on a public crack dataset
- 02U-Net segmentation for pixel-level crack outlines
- 03Length and width estimates from the crack mask
- 04Severity grading to prioritise inspections
- 05Per-class F1 and IoU reported in the evaluation
Module breakdown
- 01
Data
Public crack images split, balanced and augmented.
- 02
Classifier
Transfer-learned CNN for cracked versus intact.
- 03
Segmentation
U-Net producing crack masks.
- 04
Measurement
Skeletonisation for length and width.
- 05
Inspection app
Flask upload with annotated output and report.
After this, you will be able to
- Explain the difference between classification and segmentation
- Defend your crack measurement method and its limits
- Demo an uploaded wall photo annotated in seconds
Technology stack
- Python
- PyTorch
- OpenCV
- Flask
- NumPy
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 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