Textile pilling grade
Predict an ISO pilling grade from a fabric image, with density and the features behind the call.
Example outputs shown for illustration. Numbers depend on your samples and protocol.
Results
Each measurement below comes from your own images, tied back to the annotated frame it came from, so results stay comparable across samples, locations, and conditions.
class
ISO grade
Each detected feature assigned to a class using the agreed rule set, shown on the image.
Example, not a claimed result
In your report: Per-feature class, counts by class, and annotated overlays.
per area
Pilling density
Findings placed in sample coordinates to reveal spatial patterns and local density.
Example, not a claimed result
In your report: Coordinate-referenced map, regional density, and representative images.
count or µm
SHAP attribution
Visible surface features detected, measured, and located against the reviewed image.
In your report: Per-feature list with size, position, and annotated overlays.
count or µm
Stage contributions
Visible surface features detected, measured, and located against the reviewed image.
In your report: Per-feature list with size, position, and annotated overlays.
Built around your image set
Use the calibrated images your team already collects, together with the locations you need to compare.
Each report includes
The artifacts your team receives, ready for review and archive.
Annotated image set
Original images with regions of interest, measurement points, masks, and finding overlays.
Measurement table
Location-indexed values, units, distributions, and QC flags in a structured export.
Method record
Calibration evidence, analysis settings, version history, and validation summary.
Confidence in every resultTraceable measurements, reviewed against your agreed reference method.
- Traceable scale
- The report records the image scale, calibration evidence, and a method-specific expanded measurement uncertainty. It does not use one product-wide accuracy number.
- Reference comparison
- The configured method is compared with your accepted reference method or reviewed annotations, and reports bias by measurement range and image condition.
- Detection performance
- Detections are evaluated against reviewed reference regions with precision, recall, and segmentation overlap, separated by the conditions that affect performance.
- Repeatability
- The locked protocol is rerun on the same inputs and on a defined repeat set. The review records variation from image acquisition, sampling, and analysis separately where possible.
What this result does not establish: Assists pilling assessment and QC review. It does not replace a certified human final grade unless validated for your fabrics.
The measurement, today
Pilling assessment compares an abraded swatch to reference photographs by eye. Grades drift between assessors and labs, and the rationale is never recorded.
What it costs
A grade below spec sends fabric back to finishing or out as seconds. Because assessors drift, the same roll can pass in one lab and fail in another, and that disagreement is expensive to settle with a customer.
From image to reviewed result
- 1
Upload the swatch
Drop a flatbed scan or macro photo of the abraded fabric. No fixed rig required.
- 2
Detect pills
A segmentation pass finds and outlines individual pills, separating them from weave texture and lint.
- 3
Grade to ISO
An EfficientNet-B0 classifier predicts the modified-Martindale grade, with pilling density per cm² alongside.
- 4
Explain the call
Grad-CAM highlights the regions that drove the grade; SHAP gives per-feature and per-stage contributions.
- 5
Review & log
Accept or adjust before the result is logged with the image, grade, density, and attribution attached.
Standards & methods
- ISO 12945-2
- ISO 12945-4
- ASTM D4970
Standards-aware workflows. ConductVision supports these methods; it does not assert certified compliance without validation on your images.
Not sure this is the right measurement?
Send a representative image and your measurement goal. A ConductVision scientist will confirm whether this is the right fit, or point you to the closer workflow, before you commit to a quote.
Related applications
Composite fiber orientation
Fiber orientation, void content, and ply defects from polished sections and CT slices.
Fiber & inclusion analysis
Count and size fibers and inclusions, with area fraction and class breakdowns.
Polymer film & membrane defects
Pinholes, bubbles, scratches, and coverage uniformity for films and membranes.
Send a sample image and a measurement goal
We will show the closest ConductVision workflow and flag what needs custom validation for your images.
