Defect detection
Scratches, dents, misprints, and missing parts flagged on the line.
Vision models detect defects, count items, read labels, and check assembly steps, then record the result in your quality workflow automatically.
{
}
Scratches, dents, misprints, and missing parts flagged on the line.
Pallets, cartons, and items counted from images.
Lot numbers, expiry dates, and serials read and checked against the ERP.
Protective equipment checks and restricted-area alerts.
Visual inspection is one of the most repetitive jobs in any factory or warehouse. An inspector looks at the same kind of part hundreds of times a shift, searching for scratches, dents, missing components, or a misprinted label. Attention drops as the shift goes on, and defects that slip through are found by customers instead.
Computer vision models are well suited to this work. Given a fixed camera, consistent lighting, and enough examples of good and bad items, a model can check every unit at line speed and never get tired. It does not replace the inspector's judgment; it handles the routine checks and passes uncertain cases to a person.
Most vision projects succeed or fail before any model is trained. Camera placement, lighting, and how defects are labeled matter more than the choice of algorithm. We spend the first weeks of every project getting those right.
| Approach | What it does | Best for |
|---|---|---|
| Classification | Labels a whole image as good, defective, or a defect type | Single parts photographed one at a time |
| Object detection | Finds and boxes each item or defect in an image | Counting, missing components, multiple items |
| Segmentation | Marks the exact pixels of a defect or region | Measuring defect size or area |
| Anomaly detection | Learns what normal looks like and flags anything else | Rare defects with few examples |
| OCR | Reads printed text, codes, and numbers | Labels, lot codes, expiry dates, serials |
Industrial or IP cameras triggered by sensors or line timing, with fixed lighting.
Models run on a small computer near the line, so decisions take milliseconds and work offline.
Pass, fail, or review, mapped to an action such as a reject gate, a light, or an operator alert.
Results, images of failures, and confidence stored against the production order.
Quality teams see defect rates by line, shift, and product, with example images.
Step 01
Look at the line, the parts, the defects that matter, and where a camera can go.
Step 02
Install a camera and lighting, and collect images under real conditions.
Step 03
Label good and defective examples with your quality team's definitions.
Step 04
Train, test on held-out images, and choose thresholds with the quality team.
Step 05
Run alongside human inspection and compare decisions before acting on them.
The most common pitfall is starting with the model instead of the setup. Inconsistent lighting, reflections, and varying camera angles cause more failures than any algorithm choice, so we fix the capture first.
The second is unclear defect definitions. If two inspectors would disagree about whether an item passes, the model will be inconsistent too, so we agree examples and rules with the quality team before labeling.
The third is deciding automatic rejection too early. Shadow runs alongside human inspection show where the model is reliable and where uncertain items still need a person.
| Measure | Why it matters |
|---|---|
| Detection rate | Share of real defects the model catches |
| False reject rate | Good items wrongly flagged, which costs time and material |
| Throughput | Inspections per minute compared with line speed |
| Review volume | Uncertain items sent to inspectors |
Think of a packaging line where a misprinted lot code or a missing seal occasionally reaches customers. A camera above the conveyor photographs each pack, a model checks the seal and reads the printed code, and the result is compared with the production order in the ERP.
Packs that fail are diverted for inspection, and each failure is saved with its image against the batch. The quality team sees defect rates by shift and can trace problems to a specific machine setting.
Success is fewer defects reaching customers, inspectors focusing on the uncertain cases, and a quality record with images that explains every rejection.
Vision models, like other AI, make mistakes with a measurable rate. NIST's AI Risk Management Framework, released in January 2023 for voluntary use, provides a structure for managing those risks across an AI system's lifeSource [1]. For inspection systems, that translates into concrete practices: measure error rates on your own images, set thresholds by defect severity, and route uncertain cases to people.
We keep every image, result, and override, so quality teams can review decisions and the model can be retrained on real corrections. A pilot on images from your actual line, lighting, and cameras is the only reliable way to judge viability.
Manufacturing
Odoo MRP for manufacturers: multi-level BoMs, work centers, quality checks, maintenance, and shop-floor apps tied to finance.
AIAI in your ERP
Embed AI in Odoo workflows: smart bank reconciliation, anomaly detection, document capture, and suggestions inside the screens users know.
DevOpsCloud architecture
Cloud architecture on AWS, GCP, Azure, and bare metal: landing zones, networking, Terraform, cost control, and hybrid setups.
Next step
Thirty minutes with an engineer, no slide deck required. You'll leave with a clearer picture, whether or not we work together.