addaScan home
Guide

Manual inspection or camera inspection: what to automate first

For quality and production managers deciding which checks to leave with people and which to give to a camera.

By addaScan engineering teamTechnical review: Frank GuoPublished 8 min read

Ask which of your checks to automate
// Short answer

Manual inspection is strong on judgement, new faults and exceptions, but the research literature treats human inspection error as reducible, not avoidable, especially for rare faults over long, repetitive shifts, and interval checks miss faults between two checks. Camera inspection checks every unit against the same limits but finds only visible, defined faults. Automate first the checks that are defined, visible, frequent and costly to miss, such as labels, codes and caps, and keep people for reviewing rejects and fixing causes.

Key points

  • People are good at judgement, new faults and exceptions; cameras are good at the same defined check on every unit.
  • The research literature treats human error in inspection as something that can be reduced but not eliminated.
  • Checks at intervals miss faults that start and stop between two checks.
  • Automate first the checks that are defined, visible, frequent and costly when missed: labels, codes, caps.
  • Keep people for reviewing rejects, new products, judgement calls and fixing the cause.

What people do well

Experienced inspectors notice things nobody told them to look for: a new kind of fault, a smell, a pack that feels wrong. They judge borderline cases with context, adapt instantly to a new product, and, most importantly, find and fix the cause. No camera replaces that.

Where manual inspection struggles

A literature review by Sandia National Laboratories sums up decades of research: human inspectors are imperfect, and inspection error can be reduced with appropriate interventions but cannot be eliminated. Error rates of 20 % to 30 % are frequently quoted in the inspection literature across many kinds of inspection task, and even 100 % inspection does not find every defect (See, Visual Inspection: A Review of the Literature, Sandia 2012).

The same review reports that inspection accuracy suffers as defects become rarer, and that performance over long, repetitive watches tends to decline most for rare events, difficult detection tasks and tasks without feedback. It also notes a debate about how far those laboratory findings apply to real inspection, where how visible the defect is and how complex the decision is may matter most (See, Visual Inspection: A Review of the Literature, Sandia 2012). On a packing line, that describes a person checking labels for a mix-up that happens rarely, on every pack, for a whole shift.

Checks at intervals add a second gap: a coder that fails between the 10 o’clock and the 10:30 check prints bad codes for up to half an hour before anyone looks. The usual reports sound familiar: “label check every 30 minutes and at every reel change”, “sign off dozens of labels a day on top of the rest of my work”.

What a camera adds, and where it stops

A camera station checks every unit at line speed against the same limits, keeps counts and images for each batch, and stops or rejects on the first bad pack. It does not get tired, but it only finds what it was set up for: visible faults with limits agreed on real samples. It needs a recipe for each product, it produces some false rejects, and it cannot notice a new kind of fault the way a person can.

Side by side

Manual inspection and camera inspection compared
AspectManual inspectionCamera inspection
CoverageSamples at intervals, or 100 % at limited speedEvery unit at line speed
ConsistencyVaries between people, shifts and over timeThe same limits on every unit, until the recipe is changed
New or unusual faultsStrong: people notice what they were not told to look forWeak: finds what it was set up and trained for
Judgement callsStrong, with experienceOnly within limits agreed in advance
RecordsSign-off sheets and check formsCounts, results and images per batch
ChangeoversQuick to adapt; relies on trainingNeeds a recipe for each product; selected by the PLC
What it cannot seeFast, small or rare faults; hidden featuresAnything not visible to the camera; faults it was not set up for

What to automate first

Automate the checks that are defined, visible, frequent and costly to miss. On most packaging lines that means labels after changeovers, date and batch codes, and caps and tamper bands. Leave judgement-based and non-visual checks with people.

Which inspection checks to automate first
CheckCost of a missSuited to a camera?Suggestion
Wrong label or packaging after a changeoverHigh: recall and allergen riskDefined and visibleAutomate early
Missing, unreadable or wrong date and batch codesHigh: legal and recall scopeDefined and visibleAutomate early
Missing or crooked caps, missing tamper bandsMedium to highDefined and visibleAutomate early
Counts in open packs and traysMediumDefined when items are visibleGood candidate
Cosmetic surface marks with no clear limitVariesNeeds agreed limits firstAgree limits, then decide
Taste, smell, texture, internal faultsVariesNot visible to a cameraKeep other methods

People and cameras together

  • The camera checks every unit; people review the rejects. Rejected packs and their images tell the team what is going wrong and whether limits need attention.
  • People set up new products. Teaching a new recipe on samples is a trained task for the site team or the integrator.
  • People test the station. Challenge tests with marked test packs prove the camera and the reject still work.
  • People fix the cause. The station reports the symptom; the setter, the coder technician or the supplier fixes it.

Skills and shifts in South African plants

South African packaging trade press describes a skills shortage in which many experienced operators, artisans, setters and supervisors are approaching retirement, and some of the skills plants need are not found locally (Packaging & Print Media, “Mind the gap”). Automating a repetitive visual check frees scarce experienced people for the work only they can do. It does not remove the need for them: someone still has to set up, test and look after the station.

How a station is chosen, tested and supported is described in how we deliver a project, and the checks themselves under inspection applications.

// FAQ

Questions about manual and automated inspection

What is automated visual inspection?
Automated visual inspection uses cameras, lighting and software to check every unit on the line against defined limits and to tell the PLC which units to reject. Automated visual inspection systems range from a single vision sensor or smart camera for one check to multi-camera stations. They find visible, defined faults, not judgement-based ones.
Do visual inspectors catch every defect?
No. A Sandia National Laboratories review of the inspection literature concludes that human inspection error can be reduced but not eliminated, and that even 100 % inspection does not find every defect. Rare faults, long repetitive checking without feedback and pace make misses more likely.
Is automated visual inspection more accurate than manual inspection?
Not in every case. For a defined, visible fault a camera applies the same limits to every unit at line speed, which people cannot sustain. For new, unusual or judgement-based faults, experienced people are better. The right answer is decided per check, on your own products.
How often should labels and codes be checked manually?
Sites usually check at start-up, at every changeover and reel change, and at set intervals set by their own risk assessment. Any fault that starts and stops between two checks is missed, which is why high-risk checks such as labels and codes are often automated on every unit.
Why do manual inspectors miss defects?
The inspection literature points to several factors: defects that are rare, hard to see or complex to judge, long periods of repetitive checking without feedback, often described on the floor as inspector fatigue, and pace. Training, aids and good lighting reduce errors but do not remove them.
Should production operators do quality checks?
Operators can do simple checks well when the check is defined, quick and part of the rhythm of the line. Checks that need concentration on rare faults for long periods are where errors grow, and where a camera takes over the repetition while people handle the exceptions.
Does automated inspection replace inspectors?
It replaces repetition, not judgement. People are still needed to review rejects, set up new products, run challenge tests, and find and fix the cause of faults. Where inspection labour really stops, it is a saving; where people move to other work, it is not a cash saving.

Sources

  1. Judi E. See, Visual Inspection: A Review of the Literature (SAND2012-8590), Sandia National Laboratories, 2012 (report, p.15, §3.1.1, §3.2.5, read 2026-09-25)
  2. Packaging & Print Media: Mind the gap (South African trade press, read 2026-09-25)
// Next step

Which of your checks should a camera take over?

List the checks your team does today and how often. We will say which are defined and visible enough for a camera, and what a sample test would show.

Start an assessment