Glove inspection checks every glove for holes, tears, thin spots, stains and particles before it is packed. Cameras inspect gloves on the former line or after stripping, reject defective ones automatically, and give the plant defect data by line and former, which manual checks cannot provide at glove-line speeds.
Automated glove inspection uses cameras and lighting to examine gloves for defects at production speed. It is used on examination, surgical, household and industrial gloves made from natural rubber latex, nitrile and other polymers.
Glove lines run very fast, with thousands of formers per line, so manual visual inspection can only ever be partial. Vision inspects every glove, either on the former, where a defective glove can be marked and its former flagged for cleaning, or after stripping, where it can be rejected before packing.
Vision inspection complements, rather than replaces, the quality tests that standards require. Medical gloves are still sampled and water-leak tested for freedom from holes under EN 455-1 or ASTM D5151, with AQL sampling to ISO 2859-1. Vision reduces how many defective gloves reach that sample in the first place.
Gloves are imaged on the formers as they pass the station, or flat on a conveyor after stripping.
Backlighting through the film reveals holes, thin spots and particles; reflected light shows stains, discolouration and surface faults.
Rule-based tools catch clear defects; deep learning trained on good gloves catches subtle and variable ones.
Defective gloves are rejected or marked, and the former that produced them is identified for cleaning or replacement.
Defect counts by line, former and defect type show when dipping, leaching or curing conditions are drifting.
Light shining through the glove film makes holes bright and thin spots lighter, and shows embedded particles as dark marks.
Light from the camera side reveals stains, discolouration, surface roughness, flow marks and cuff bead defects.
Each image is tied to a former position on the chain, so repeat defects point to a specific former that needs attention.
A model trained mostly on good gloves learns normal variation in colour, texture and shape, and flags anything unusual, which suits rare and varied defects.
Cameras are synchronised to the line so every glove is imaged, even at full production speed.
Two example project scopes showing how the station, the checks and the outputs are defined. Every plant is different, so the final configuration is confirmed after a feasibility study on your own parts.
The situation: A glove manufacturer runs fast nitrile lines and finds defects mainly at AQL sampling, too late to correct the process for that lot.
The situation: A household glove maker packs gloves by hand and wants consistent cosmetic and hole checks before packing.
Industrial cameras, lenses, line-scan cameras and code readers are available through our machine vision catalog, quoted with delivery to Sri Lanka. We select the hardware for your application during the feasibility study.
Browse the hardware catalogEvery product, surface and line behaves differently under a camera, so every project starts with evidence from your own material.
A site visit to understand your product, line speed, quality criteria and where the check should sit.
We image your good and defective samples and show what the system can reliably detect. This is the go or no-go.
One station on one line, running beside your inspectors until results match and your team trusts them.
More lines, integration with your PLC and systems, and local support from our Sri Lankan engineering team.
Automated surface inspection for scratches, dents, cracks, porosity, stains and coating faults on metal, plastic, rubber and glass. Specialised lighting and deep learning find cosmetic and functional defects on every part.
AI on your CCTV detects missing helmets, vests, gloves and hairnets, danger zone entry, forklift near misses and smoke. Processed on site, PDPA ready.
Automatic counting of parts, garments, cartons and packs by camera, sensor or weight, with counts sent to your PLC or ERP. Designed and built in Sri Lanka.
Sort fabric rolls, cut panels and washed garments into buyer shade bands with CIELAB measurement and 555 codes.
Every machine vision application we design and build, in one place.
Yes. Backlighting through the glove film makes holes appear as bright spots, and thin areas as lighter regions. The smallest detectable hole depends on camera resolution, glove colour and line speed, which we confirm on your gloves during the assessment.
No. For medical gloves, freedom from holes is tested on samples by water leak testing under EN 455-1 or ASTM D5151, with AQL sampling to ISO 2859-1. Vision inspects every glove on the line, so fewer defective gloves reach the sample and lots are less likely to fail.
Yes. Inspecting on the formers lets the system identify which former produced a defect, so dirty or damaged formers can be cleaned or replaced before they produce more rejects.
Yes, but lighting and models are set up per colour and material, since blue nitrile, white latex and black gloves behave differently under backlight and reflected light.
Cameras are triggered from the line so every glove is imaged at full speed. Very fast lines may need more than one camera per side or per lane, which is decided in the design.
Tell us what you need to check and share some good and faulty samples. We will show you what a camera can reliably see before you commit to anything.
Photographs show representative plants and equipment, not Cerox installations or client sites. Diagrams by Cerox Engineering. Photo credits, via Wikimedia Commons: Nitrile glove by BlueThunderTechnologies, CC BY-SA 4.0; Lab technician putting on protective gloves by Shixart1985, CC BY 2.0.