Mini-project
Manufacturing, Robotics & Industry 4.0
Fabric defect detection for a textile mill
Find holes, stains and broken threads on fabric images, and count defects per roll.
The brief
Textile mills lose money when defective cloth reaches the customer, and inspectors tire quickly. Train a model to find and classify fabric defects in images, count defects per metre, and decide whether a roll is first grade or second grade by a points system. Good looks like: defects found on fabrics the model has not seen, a count and grade per roll, and a speed that could keep up with a loom.
What you will build
- Collect fabric images with and without defects
- Label defects
- Train an anomaly or detection model
- Test on new fabric patterns
- Apply a four-point grading system per roll
- Measure speed per metre
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.