Product and empty-tray area segmentation for food portions
Portion coverage on a food tray changes with shape; a package box or single product detection does not isolate empty-tray fraction. Film glare can affect the target mask.
Show product and empty-tray masks together with coverage and excluded glare area. Hold a portion outside visible-coverage limits for operator review.
- 01 Position
- 02 Raw image
- 03 Mask generation
- 04 Region calculation
- 05 Decision
Register the ROI; occluded areas are excluded from visible-area calculations.
- Target-mask area
- —
- Connected regions / objects
- —
- Decision metric
- —
Scenes are illustrative simulations; they are not customer references or performance guarantees.
Solution approach
Pixel or instance masks are derived from the raw image; a coded legend separates background and target regions. Area fractions use only the visible ROI. Mask product, tray and glare-exclusion regions separately and compare visible product area. Weight is not inferred from pixel area.
Process steps
- 01
Position
Register the ROI; occluded areas are excluded from visible-area calculations.
- 02
Raw image
Keep the controlled raw image in a separate panel.
- 03
Mask generation
Coded colours show target classes or object identities.
- 04
Region calculation
Derive area fraction, connected regions and the decision metric from the mask.
- 05
Decision
Hold an out-of-limit sample for review with its local region marked.
Related applications
Let us assess your application together
We test your sample in our laboratory and report on resolution, optics and lighting selection.