Line image
INPUT · RAW
Unprocessed camera image of the panel passing through the line.
Furniture · Panel & Assembly · Quality Control
Quality control that checks every panel against a reference before it ships.
A light-isolated edge station installed on the panel and assembly line compares every part with a learned perfect reference in real time. It catches surface scratches, stains, edge-band misalignment, and missing fasteners, then stops the line or alerts the operator.
LIVE · LINE 01INSPECTION ACTIVEPANEL EXIT · CONVEYORPANEL & ASSEMBLY LINE · CONVEYOREDGE · ON-DEVICEREFERENCE · LOADED
Technical Specifications
Panel surface and assembly integrity in one enclosed station
Request a quote →| Installation | Light-isolated enclosed station above the conveyor |
|---|---|
| Inspection method | Real-time comparison against a perfect reference panel |
| Processing | Edge / on-device — no cloud dependency |
| Surface types | Melamine / lacquered panel · upholstery fabric · woven cane · acoustic panel |
| Detected defects | Scratches, dents, stains, coating blisters, edge-band overrun, delamination |
| Presence – absence | Verification of holes, grooves, dowels, cam fittings, and fasteners |
| Color and pattern | Tone difference, pattern direction, and texture deviation checks |
| Anomaly threshold | Customer-adjustable sensitivity and acceptance limit |
| Defect classification | Type-based labels (scratch / stain / edge band / missing part, etc.) |
| Multiple products | Profiles saved per product code, switched from the panel in one touch |
| Action outputs | Line stop · siren / light · PLC / relay · operator notification |
| Logging & reports | Time-stamped images · daily / weekly / monthly reports |
| Visual evidence | Original image + anomaly heatmap + confidence score |
| Integration | Added to an existing panel / assembly line as an independent station |
Reference · Comparison
The perfect panel is taught, and every other panel is measured against it.
A reference panel meeting your acceptance criteria is introduced to the system first. That reference holds the surface texture, color tone, edge-band line, and hole pattern. Every panel on the line is compared against this profile; deviations are marked on an anomaly map and converted into a numeric confidence score. Surface quality moves out of personal judgement and onto a measurable criterion.
Anomaly map
DETECTION · HEATMAP
The region deviating from the reference is marked and its score checked against the acceptance threshold.
Core Capabilities
Designed for panel, board, and assembly lines.
Reference-based inspection
A perfect panel is learned and every deviation is measured against it.
Enclosed station
Light isolation provides stable, repeatable imaging.
Edge processing
On-device analysis preserves low latency and data privacy.
Edge-band inspection
Band continuity, overrun, and drift are tracked without gaps along the surface.
Presence – absence checks
Holes, grooves, and fasteners are verified before assembly.
Adjustable threshold
Sensitivity and acceptance limits are configured per product.
Color and pattern consistency
Tone difference, pattern direction, and texture deviation are compared across batches.
Visual evidence
The source image, heatmap, and confidence score are stored together.
Easy integration
Added to the line as an independent inspection station.
How It Works
From reference to action in four steps.
Teach the reference
The perfect panel's surface, color, and hole profile is saved with the product code.
Capture in-line
Every panel is imaged under controlled lighting inside the enclosure.
Compare & score
Deviations are mapped and converted into a confidence score.
Threshold & action
When the threshold is exceeded, the system alerts or stops and records the defect.
From the Field · Detections
Detections from the field
The examples below show anomaly heatmaps produced by the system.
ORIGINAL + HEATMAP
Tear in upholstery fabric — loss of continuity in the weave.
ORIGINAL + HEATMAP
Hole in woven cane — local loss of texture on the surface.
ORIGINAL + HEATMAP
Surface stain — local color deviation against the reference batch.
Detected Anomalies
Three families of deviation on a panel.
Surface, edge, and assembly integrity are all inspected in the same pass, against the same reference.
Surface defects
Scratches, dents, stains, coating blisters, and delamination; deviations that spoil the visible surface.
Edge and band defects
Edge-band overrun, drift, detachment, and loss of continuity at corner transitions.
Missing part / assembly error
Missing holes, grooves, dowels, and fasteners, plus incorrect positioning.
Action Outputs
The action you need at the moment of detection.
Alert only, alert plus stop, or full automation—the system is configured for your production scenario.
Line stop
Automatically stops the line through relay / PLC integration.
Audible alert
Immediately warns the operator with a siren or alarm.
Visual alert
Signals with a lamp or tower light.
Operator notification
Shows the alert and defect image on screen.
PLC / automation
Provides outputs compatible with existing automation.
Logging & reports
Time-stamps detections and includes them in periodic reports.
Line Integration
Add it to your panel line without redesigning production.
Independent station
The enclosure is positioned directly above the conveyor.
Multiple product profiles
Panels are saved by product code and recalled quickly.
Controlled lighting
Stable images are captured independently of ambient light.
Automation-ready
PLC and relay outputs connect to existing infrastructure.
Precision down to 6 µmProcessing edge / on-deviceCloud not requiredInspection 100%, not sampled
Any product that travels along a conveyor or extrusion line, or is checked in a fixed cell, can be inspected. Defects, presence–absence, dimension, angle, shape, fill level, and surface — in short, every deviation beyond the defined standard is detected.
Configured for your line
Let's plan in-line quality control for your panel operation.
Tell us about your panel, line speed, and acceptance criteria. We'll propose the right installation, thresholds, and action scenario.