Connector class probabilities and unknown-variant quarantine
Connectors with identical housings but different pin layouts can mix in an assembly recipe. Forcing an unseen type into the nearest known class can accept the wrong part.
Link variant class, confidence score and quarantine reason to the pallet identity; release the expected type and hold other types with evidence for review.
- 01 Recipe
- 02 Raw image
- 03 Class scores
- 04 Confidence gate
- 05 Route
Load the class expected by the order.
- Top class score
- —
- Top-two class gap
- —
- Hold for review
- —
Scenes are illustrative simulations; they are not customer references or performance guarantees.
Solution approach
The controlled image ROI is classified; the raw image and C1/C2/C3 scores appear separately. The order class and confidence threshold are evaluated together. Assess layout class beyond pin count and show three scores plus the class gap. Hold an unknown layout as UNKNOWN.
Process steps
- 01
Recipe
Load the class expected by the order.
- 02
Raw image
Trigger the specimen under fixed lighting and link the image to its ROI.
- 03
Class scores
Reveal the three illustrative class scores as comparative bars.
- 04
Confidence gate
A low score becomes UNKNOWN; a confident wrong class is also not accepted.
- 05
Route
Release the accepted example and transfer the others to the review nest.
Related applications
Let us assess your application together
We test your sample in our laboratory and report on resolution, optics and lighting selection.