MANUFACTURING
Assembly Verification
Assembly Verification. What it takes to run it.
Confirming correct part placement and orientation in real-time.
// 01 · The question
“Is every part present, in the right place, the right way round?”
// 02 · Why it is hard
It is a completeness check, which means the absence of a small part in a cluttered assembly is the signal. Absence is harder to score than presence and easier to miss under partial view.
// 03 · What the labels have to be
Bounding box
Decided before the first frame
Presence, position and orientation are all read from a box and its aspect. There is no measurement of extent here, so segmentation adds labelling cost without changing a single pass or fail.
This is the decision that is expensive to reverse. The geometry has to match what the answer contains, and finding out it does not means labelling the set a second time.
// 04 · How we run it
Three parts of one loop, on this job.
LexAnnotate
Defect Annotation
Pixel-level defect annotation for surface scratches, cracks, dents, weld faults, and assembly misalignments. Multi-sensor alignment for multi-camera inspection systems.
LexInsight
Line Performance
Connect defect detections to production data - batch numbers, machine IDs, shift schedules. Identify defect patterns across lines and predict maintenance needs before unplanned downtime.
LexAlert
Quality Alerts
Monitor defect detection accuracy across changing production conditions. Detect when lighting shifts, new materials, or equipment aging degrades model performance. Auto-retrain to maintain 99%+ accuracy.
// 05 · What breaks it after launch
A second plant builds the same product with a different fixture, a different camera height and a different ambient light. Nothing about the product changed, and the model does not transfer.
It is not the only one that can get this use case, it is the one that usually gets it first. All ten conditions.
// 06 · In manufacturing
Defect Detection at Scale
The Challenge
Vision models performed well in pilots but lost accuracy as factory conditions shifted.
Our Execution
Built pixel-level annotated datasets and multi-sensor alignment for reliable defect detection.
The Result
Maintained 99%+ defect detection accuracy across changing production environments. Reduced unplanned downtime.
99%+
Accuracy maintained in production