Surface defect detection
Scratches, dents, cracks, stains, voids and coating flaws on metal, plastic, glass, textiles and painted parts.
Home/Solutions/Industrial Vision QA
Edge AI · NVIDIA Jetson
AI visual inspection that runs on NVIDIA Jetson, right beside the camera. Find scratches, dents, missing components and misprints in milliseconds, and reject bad parts before they leave the line. No video has to leave your plant.
What we build
Rule-based machine vision breaks when lighting, materials or suppliers change. Deep-learning inspection learns what good looks like, and keeps learning on your line.
Scratches, dents, cracks, stains, voids and coating flaws on metal, plastic, glass, textiles and painted parts.
Missing, misplaced or wrongly oriented components, connectors and screws. PCB inspection for solder and placement defects.
Lot and date codes, labels, serials, barcodes and DataMatrix codes read and verified against your MES records.
Dimensions, gaps, fill levels and alignment checked with calibrated cameras, combined with AI for the hard cases.
Train mostly on good parts when defect samples are rare. The model flags anything that does not look normal.
PPE checks, restricted zones and person-near-machine alerts using the same edge AI hardware and pipeline.
From camera to reject gate
Industrial cameras, lenses and lighting chosen for the defect. Image capture triggered by encoder or PLC.
Labelled and synthetic defect images, fine-tuned from NVIDIA pre-trained vision models with the TAO Toolkit.
Pruning, distillation and FP16 or INT8 quantization so the model fits the Jetson and the cycle time.
Multi-camera inference at the edge. Pass or reject sent to the PLC over digital I/O, Modbus or OPC UA.
Uncertain images go to review, models retrain, and new versions roll out over the air through the ARP Device Cloud.
Why the edge
A reject gate cannot wait for a round trip to the cloud. Running inference on NVIDIA Jetson next to the camera keeps decisions fast, private and available.
Hardware sized to the line
Where it works
Component presence and polarity, solder bridges, tombstoning, and conformal-coating coverage.
Machined, cast and moulded parts checked for surface flaws, burrs, porosity and missing features.
Label, seal, cap and fill-level checks with code verification for traceability.
Foreign objects, shape and colour grading, pack integrity and print quality.
Continuous web inspection for weaving faults, stains, holes and pattern drift.
Cracks, cold shuts, scale and coating defects on hot or reflective surfaces.
How we engage
Send us good and defective samples. We test optics and models and report what is detectable, and how reliably.
One station on your line, running alongside manual inspection so results can be compared.
PLC integration, operator screens, MES reporting and validation documents for each station.
Review queues, retraining and over-the-air model updates keep accuracy high as products change.
NVIDIA, Jetson, Metropolis, DeepStream, TAO and TensorRT are trademarks of NVIDIA Corporation. The demo on this page uses simulated data.
Send us a few samples. We will tell you whether AI can find it, and what a station would need.