Machine Vision Inspection Systems for Production Lines

Motionwell Automation integrates machine vision inspection into custom machines and existing production lines in Singapore. Delivered systems include multi-point inspection on a 12-station rotary medical assembly machine running a 15-second cycle (P22068), inspection inside cleanroom automated test equipment (P23018), vision and a collaborative robot in a QA lab automation cell reordered four years running (P23078 through P26078), and a copper-plate thickness measurement machine built around a Keyence displacement system in 2026.

A machine vision inspection system is a camera, a lens, a light source and a processor that makes a pass, fail or measurement decision on every part while the line runs, then hands that decision to the machine controller so something physical happens: a pusher fires, a gate diverts, a record is written. The camera is the cheap part. The engineering sits in the lighting, the fixture that presents the part the same way every cycle, and the handshake that makes the result act before the part is gone.

That description holds across industries, and this page stays at that general level. Where the question is electronics-specific — sizing a camera across a panel, connector pin coplanarity, mixed surface finishes in one field of view — the detail is in our separate guide to vision inspection for electronics.

This page is written from the integrator’s side of the table: choosing hardware, lighting the part, knowing what vision cannot see, and tuning the false-reject trade-off so operators don’t switch the station off. If you already have parts and a defect list, talk to an engineer.

What Is Machine Vision, and How Does It Work?

Machine vision is automated visual inspection under controlled conditions. Every system, from a single smart sensor to a multi-camera line, runs the same chain:

1. Trigger. A sensor, encoder pulse or PLC output tells the camera a part is in position. Everything downstream inherits the trigger’s jitter.
2. Illumination. A light fires, usually strobed, creating contrast between the feature you care about and everything else.
3. Capture. The lens projects the scene onto the sensor. Blur length is roughly part speed times exposure time, so a moving part forces short exposure, which forces more light.
4. Processing. Software locates the part, applies measurement or defect tools inside regions tied to that located position, and produces numbers: an edge distance, a match score, a blob area, a code grade.
5. Decision. Those numbers are checked against limits, and a pass/fail bit plus the measured values go to the PLC over EtherNet/IP, PROFINET or digital I/O.

Step 4 gets all the attention in marketing material. Steps 1 to 3 cause almost all the field failures.

Machine Vision vs Computer Vision

The distinction is practical, not academic. Computer vision is the general problem of extracting information from images, often in scenes nobody controls. Machine vision is the industrial subset: fixed camera, fixed lighting, a part held in a known position by a fixture we designed, and a decision that lands inside a cycle time with a deterministic output.

That constraint is a feature. A line doesn’t need a clever answer, it needs the same answer at 3 a.m. with a different operator and a different lot of material. Much of the integrator’s job is removing variation until the vision problem becomes easy.

Should You Use a Smart Camera or a PC-Based System?

This is the first hardware decision, and it sets your spare-parts strategy for the next decade.

We specify smart cameras for most stations because the maintenance story is better. When a Keyence or Cognex unit dies at 2 a.m., a technician swaps the body and reloads a stored recipe; when a PC-based system dies, someone needs the drive image, the licence and the right software version. PC-based wins when several cameras must see one part in the same instant, when resolution outruns a smart camera sensor, or when the quality system requires an archived image of every part.

Keyence is the platform we buy most, chosen for setup speed and local support. We first bought Cognex DataMan readers in 2026 for serialization, where DataMatrix grading against ISO/IEC 15415 matters more than defect tooling. Both integrate the same way: trigger in, result out, recipe selected by the PLC.

Why Does Lighting Decide Whether the System Works?

If a defect is not visible in the raw image, no amount of processing recovers it. Lighting is not an accessory to the camera. It is the measurement instrument, and the camera only records what the light reveals.

Contrast comes from geometry. The same scratch is invisible under flat front light and obvious under grazing illumination: light striking a raised edge at a low angle scatters back toward the lens, while the flat surface reflects away.

Two rules on every build. Shroud the station so factory ambient light and sunlight through a roller shutter never reach the field of view — a station that drifts between day and night shift is almost always an ambient light problem. And fix the part mechanically: a camera can’t compensate for a part that rocks in its nest, it reads that rocking as dimensional variation and scraps good product. On the rotary assembly machine (P22068), nest design took longer than vision setup.

How Do You Choose Optics and Working Distance?

Working distance, field of view and sensor resolution are locked together: fix any two and the third follows.

Start from the smallest feature you must reliably detect. Divide field of view width by horizontal pixel count to get millimetres per pixel. A widely used industry rule is that the smallest defect needs at least three pixels across it, and more when contrast is low, because a one-pixel feature is indistinguishable from sensor noise. Work backwards to the sensor, then pick a focal length giving that field of view at a working distance the machine frame can accommodate.

• Depth of field. Closing the aperture deepens focus and cuts light reaching the sensor, pushing you toward more illumination or longer exposure. On parts with height variation, depth of field is often the binding constraint, not resolution.
• Perspective error. A standard lens images the top of a tall part at slightly different magnification than the bottom, so a dimensional check reads differently as the part shifts. Telecentric lenses remove that change and are the normal choice for measurement.
• Mounting. The lens must clear the robot envelope, gripper swing and the operator’s hand. Vision layout freezes with the machine layout, not after it.

Not every measurement problem is a camera problem. The copper-plate thickness machine we delivered in 2026 uses a Keyence laser displacement system, because triangulation measures height directly better than a 2D image infers it. Our leak-test fixtures use SICK sensing, because a leak has no visual signature. Picking the sensor that suits the physics is part of the job.

What Defects Can Vision Catch, and What It Cannot?

Vision reliably catches anything that makes a repeatable difference in the image under controlled light:

• Presence and absence of a component, screw, seal, gasket or insert
• Orientation and correct part variant before an irreversible step
• Dimensional checks in the image plane against a calibrated scale
• Surface defects: scratch, dent, burr, flash, contamination, discolouration
• Barcode and DataMatrix reading plus print quality grading
• Fill level, cap presence, cap skew and seal defects on filled containers, as covered on our filling machines capability page
• Weld bead surface geometry — bead width, spatter, undercut, surface-breaking porosity. We integrate the inspection, not the welding process itself

Vision cannot see through material. Subsurface porosity, internal voids, delamination and cracks under coating need X-ray, ultrasonic or CT. Leaks need pressure decay or tracer gas. Torque, force and continuity need their own instruments. Vision also performs badly against defects with no consistent visual signature — a contamination class that sometimes reads as a shadow gives you a station that passes buy-off and drifts afterwards.

So the first step of any vision project is imaging your real parts, including known-bad ones from every defect class. If a defect can’t be shown to the camera in a way an engineer sees on the monitor, it won’t be caught in production. Our vision inspection guide for electronics covers resolution sizing in more depth.

What Does a Label Inspection System Check?

Label inspection is the most common first vision project: the defect is visible, the payback is obvious, and a mislabelled unit is a regulatory problem in medical device production and pharmaceutical packaging. A label inspection system typically verifies:

• Presence and position. Label applied, within skew and placement tolerance, no lifted corners or wrinkles.
• Correct variant. Artwork matches the batch recipe, catching the classic changeover error of running yesterday’s label on today’s product.
• Print legibility. OCR or pattern matching on lot code, expiry date and product name, with OCV confirming the printed string equals what the line was told to print.
• Code quality. Barcode and 2D code decoded and graded, so a code that still scans but is degrading gets flagged before it fails at a distributor.

The hard part is rarely the reading. It’s presenting a curved, glossy, sometimes translucent surface to the camera consistently while the container moves — a lighting and handling problem before it’s a software one.

How Do You Balance False Rejects Against False Accepts?

Every inspection tool produces a continuous score — a match percentage, a blob area, an edge distance — and a threshold turns it into pass or fail. Tighten it and you fail more good parts. Loosen it and escapes rise. No setting removes both; there is only the setting that fits the cost of each error.

Those costs aren’t symmetric. Where an escape can reach a patient or trigger a recall, the threshold sits tight and scrap is accepted. On high-volume consumer goods, a false-reject rate of a few percent eats the margin, so the threshold loosens and a manual check catches the rest.

How we set it:

1. Collect a real sample set including borderline parts. Clean good parts and obvious defects say nothing about where the threshold belongs. The marginal parts define it.
2. Grade that set by hand first, ideally with two inspectors. If experienced people disagree on a part, the vision system won’t be more consistent than the specification it copies.
3. Plot the score distributions for good and bad. The overlap is the real information: heavy overlap means the lighting or optics needs rework, not that the threshold needs a nudge.
4. Set the threshold, then validate against a held-back sample the station has never seen.
5. Log every reject with its image and score, or nobody can say later whether a rising reject rate is a process problem, a lighting problem, or a drifting threshold.

The failure mode we see most often is a station tuned for zero escapes on marginal illumination. Reject rate climbs, production falls behind, and someone eventually widens the limits until everything passes. A station operators trust beats one that is theoretically stricter.

How Does Vision Connect to Rejects and Traceability?

A pass/fail bit that nothing acts on is a screensaver. The mechanical and data side is where the station earns its keep.

Reject actuation. Pneumatic pushers and air blasts suit small parts at speed, diverter gates and drop flaps suit larger items, and a robot pick-off handles parts that must be placed rather than dropped, or rejects segregated by defect class. We build these with SMC and Festo pneumatics, driven by the machine’s own PLC.

Reject confirmation. The reject device needs its own sensor proving the part actually left the line. Without it, a stuck pusher silently passes every failed part downstream while the log still records a rejection. On regulated lines this isn’t optional.

Timing. Several stations usually sit between camera and reject point, so the PLC carries each result along with its part in a shift register indexed to the conveyor encoder or machine cycle. Get this wrong and rejects land one position off — which looks like a vision fault and isn’t.

Data. Results go to CSV, a database or an MES. On serialization lines we pair Cognex DataMan readers with Domino coders so every code is printed, read back, graded and bound to the unit record. For a medical device manufacturer we delivered an electronic device history record system as a standalone order, now rolling out site by site, so inspection results attach to the unit’s build history instead of a local log file. Where 21 CFR Part 11 applies, audit trail and controlled retention get designed in, not bolted on at validation.

The cleanroom automated test equipment case study shows the pattern inside an enclosed, fan-filtered machine: cobot loading, fixture test, inspection, logging, segregated output.

Working With a Machine Vision Integrator in Singapore

Straight about what we are: Motionwell is a machine builder and system integrator, not a vision algorithm house and not a camera manufacturer. We specify the camera, lens and light for your defect, design the fixture and motion that present the part identically every cycle, write the PLC logic and reject handling, and prove the result on your parts.

Vision is usually one station inside a larger machine we’re building anyway — an assembly cell, a test rig, a filling line, or a retrofit whose control system we’re modernising. That’s where integration quality matters most, because the camera shares a cabinet, a network, a safety circuit and a cycle time with everything else. We work from Woodlands Link with an in-house design team of eight, ISO 9001:2015 certification and bizSAFE Level 3. Our guide to selecting a system integrator lists the questions worth asking any vendor, including us.

Frequently Asked Questions

What does a machine vision integrator actually do?

An integrator selects the camera, lens and lighting for your specific defect, mounts them so the part presents itself identically every cycle, writes the PLC handshake, and connects the pass/fail result to a reject device and a data record. Motionwell does not manufacture cameras or write vision algorithms from scratch. We build the machine around the camera so the inspection stays repeatable at line speed.

Should I choose a smart camera or a PC-based vision system?

Start with a smart camera. A single Keyence or Cognex unit with built-in processing handles presence checks, code reading, label verification and straightforward measurement, and a plant technician can adjust it without a software engineer. Move to a PC-based system when you need several synchronised high-resolution cameras, an archived image of every part, or a classification task the vendor toolset cannot express.

Why does lighting matter more than camera resolution?

A defect the light does not reveal is invisible at any resolution. Contrast comes from geometry: low-angle light turns a scratch into a bright ridge, backlight turns an edge into a hard silhouette, a diffuse dome removes the hotspots that break OCR on glossy curved surfaces. Inspection stations that fail in production usually fail because ambient light changed or the fixture let the part sit differently, not because the camera was too small.

What defects can machine vision inspection not detect?

Anything below the surface. Subsurface porosity, internal voids, delamination and cracks under coating need X-ray, ultrasonic or CT inspection. Leaks need pressure decay or tracer gas. Vision also performs badly against defects with no consistent visual signature, such as contamination that sometimes reads as a shadow. We image your real parts, including known-bad ones, before committing to a vision approach.