Automated visual inspection on a camshaft production line
A line-side camera reads each camshaft's engraved serial number and flags surface defects in real time, logging every part for traceability.
The challenge
Manual inspection of camshafts was slow and inconsistent, and linking defects to individual serial numbers for traceability depended on paperwork.
What we built
- Bounding-box annotation of serial-number regions and polygon masks for scratches, casting marks and dents.
- A two-stage pipeline: a detector localizes the serial plate and defects, then OCR reads the serial while a classifier grades severity.
- Every inspected part logged with serial number, defect class and pass/fail, exportable for SPC dashboards and audits.
Results
- Traceability from serial number to defect record
- Reduced manual QC effort on the line
- Data ready for SPC dashboards and customer audits
Step by step.
Capture
A line-side camera images each camshaft.
Detect
The model localizes the serial plate and defect regions.
Read
OCR reads the engraved serial number.
Grade
A classifier grades defect severity and decides pass or fail.
Log
Results are logged per part for traceability and SPC.
More computer vision projects.
Real-time fire and hazard detection from video
Live and recorded camera feeds are analyzed in real time, with fire and flame events flagged and streamed to a browser dashboard.
Highway traffic counting for outdoor advertising analytics
A camera on a highway billboard counts and classifies passing vehicles, producing impressions data advertisers use for media planning.
Let's see what this could look like for you.
Tell us about your process and systems. We'll outline an approach, the guardrails it needs and a pilot plan.
© Copyrights 2026 by Techno Genesis Software Solutions Pvt. Ltd.