ROVI-SWIR · WHITE PAPER

SWIR (Short-Wave Infrared) Camera White Paper

What short-wave infrared (SWIR) — invisible to the eye and to ordinary cameras — can show, how a SWIR sensor is built, and how it is used to inspect clear film packaging, explained with diagrams and test video.

1. Summary

Our eyes and ordinary cameras see visible light, about 400–700 nm. A SWIR (Short-Wave Infrared) camera sees longer light, about 1000–1700 nm. In this band, materials such as water and plastics absorb particular wavelengths, so things that look the same in visible light show up as differences in brightness. Clear plastic film is one of them.

RGB cameraSWIR camera
Light it seesVisible, about 400–700 nm (sensor up to about 1000 nm)About 1000–1700 nm (IMX990: 400–1700 nm) (spec)
Sensor materialSiliconInGaAs (indium gallium arsenide) + silicon readout
ImageColourMono (brightness)
Good atColour, text, shapeDifferences in material — water, plastics, clear film — and what lies under visible inks
Resolution and priceHigh resolution, inexpensiveAbout 1.3 MP, expensive

In one line: RGB sees *what colour and shape* something is; SWIR sees *what it is made of*. ROVI-SWIR uses this to decide whether clear film packaging is there or not.

2. Why an RGB camera cannot do it

Clear film lets visible light through almost unchanged. In an ordinary camera, covered and bare areas look almost equally bright; what you see is the film's reflections (glare) and wrinkles. Reflections change with lighting angle and product position, so they make a poor basis for a decision.

In SWIR, the film itself absorbs and scatters certain wavelengths, so the covered area looks consistently darker. You are looking at a property of the material rather than at reflections, which makes the decision simple.

Clear film packaging seen by a SWIR camera — the film's wrinkles and edges, almost invisible in visible light, stand out
Clear film packaging seen by a SWIR camera — the film's wrinkles and edges, almost invisible in visible light, stand out

3. What SWIR is — wavelength bands

Light is named by its wavelength: about 400–700 nm is visible, 700–1000 nm is near infrared (NIR), and about 1000–1700 nm (up to 2500 nm in the wider sense) is short-wave infrared (SWIR).

visible near IR short-wave infrared (SWIR) Silicon CMOS — ordinary RGB / mono cameras about 400–1000 nm InGaAs — SWIR camera (Sony IMX990) 400–1700 nm ● water (O-H) · 970 · 1200 · 1450 · 1940 nm ● plastics (C-H) · 1210 · 1400 · 1730 nm 8 test wavelengths 1050 1100 1150 1200 1300 1450 1550 1650 400 700 1000 1300 1700 2000 wavelength (nm)
Wavelength bands and sensor sensitivity — silicon sensors stop at about 1000 nm, while the InGaAs sensor (IMX990) sees 400–1700 nm. Blue dots are where water (O-H) absorbs light, purple dots where plastics (C-H) absorb, and below are the 8 lighting wavelengths used in the FLOYD test.

4. Why materials look different

Bonds inside molecules (O-H, C-H and so on) absorb particular wavelengths, and these absorptions are concentrated in the SWIR band.

MaterialAbsorbs at (approx.)How it looks in SWIR
Water (O-H bonds)about 970 · 1200 · 1450 · 1940 nmWet or moist areas look darker
Plastics and film (C-H bonds)about 1210 · 1400 · 1730 nmEven clear film looks darker in its absorption band
Many printing inks and dyesAbsorb visible light, absorb less in SWIRWhat lies under the print shows through

Where clear film covers the product, light crosses the film twice (going in and coming back out after reflecting), being absorbed and scattered each time, so the area looks darker.

Visible light (RGB camera) light camera product surface clear film no film covered and bare areas look almost the same SWIR 1550 nm light camera product surface clear film no film covered area looks darker — presence decided by brightness
In visible light the film lets light straight through, so covered and bare areas look the same (left); at 1550 nm SWIR the light weakens as it crosses the film, so the covered area looks darker (right)

5. SWIR sensor structure

The heart of a SWIR camera is an InGaAs (indium gallium arsenide) sensor. The Sony IMX990 (SenSWIR) used in ROVI-SWIR bonds a light-absorbing InGaAs layer onto a silicon readout circuit.

LayerWhat it does
InGaAs absorption layerAbsorbs light beyond 1000 nm and turns it into charge — the band silicon cannot see
Thinned InP layerThinning the light-entry layer lets one sensor see from visible (400 nm) to SWIR (1700 nm) (spec)
Copper-copper (Cu-Cu) bondingConnects InGaAs and silicon directly at each pixel — keeps pixels small at 5 µm (spec)
Silicon readout circuitTurns charge into a digital image, with a global shutter that captures all pixels at the same instant
Cooling (TEC)InGaAs gets noisier (dark current) as it warms, so the sensor is cooled
Silicon CMOS (RGB camera)InGaAs (SWIR camera)
Sensitivityabout 400–1000 nm400–1700 nm (IMX990, spec)
Resolutionmillions to tens of millions of pixels1280 × 1024 (1.3 MP)
Pixel size1–5 µm5 µm
Noise handlingusually no coolingcooled to reduce dark current
Priceinexpensiveseveral times more

6. Lighting and choosing the wavelength

Contrast in a SWIR image is set by which wavelength you shine on the scene. Broadband lighting (halogen and the like) mixes several absorptions and blurs the contrast, so you pick a narrow-band LED or filter at a wavelength the target material absorbs.

FLOYD photographed the same product with and without film under LED lighting at 8 wavelengths from 1050 to 1650 nm and compared which wavelength separated the two best.

separation d′ (higher = easier) 0.2 0.4 0.6 0.8 0.02 1050 nm 255 / 255 0.03 1100 nm 255 / 255 0.01 1150 nm 255 / 255 0.01 1200 nm 255 / 255 0.02 1300 nm 255 / 255 0.47 1450 nm 252 / 255 0.78 1550 nm 237 / 249 0.56 1650 nm 200 / 212 saturated at this exposure (mean 255) → not measurable best separation mean brightness film / no film (0–255)
8-wavelength comparison (test, same exposure) — bars show the separation (d′, higher is easier) between images with and without film; the numbers below are the mean brightness in the inspection area (film / no film, 0–255). At 1300 nm and below the image was saturated at this exposure and no difference could be measured; from 1450 to 1650 nm the covered area got darker, and 1550 nm separated best.

7. How ROVI-SWIR decides

Instead of an AI model, ROVI-SWIR decides with a single brightness value, using the physical fact that film-covered areas get darker at 1550 nm.

1550 nm light narrow-band LED a band the film absorbs SWIR camera InGaAs 1280 × 1024 mono image Inspection area where the film should be · mean Threshold boundary between film / no-film samples Verdict Wrapped / Non Wrapped to app · signal No AI model — a few dozen samples set the boundary
ROVI-SWIR decision flow — 1550 nm light → SWIR camera → mean brightness of the inspection area → threshold → Wrapped / Non Wrapped verdict
  1. Set an inspection area where the film should be.
  2. Take a few dozen pictures of products with and without film, and set a boundary (threshold) between their mean brightness.
  3. In operation, compare each image's inspection-area mean with the boundary to decide Wrapped / Non Wrapped, and send it with a score (0–1) to the screen, the app and a signal output.
FeatureDetails
No AI trainingStart with a few dozen samples — no large labelled dataset, no GPU
ExplainableThe decision rests on one thing, how dark the inspection area is — people can check results directly
LightweightRuns in real time on an edge device
Key to stabilityFixed lighting and exposure, and an inspection area that matches where the film is

8. Test video

A test video of a cup product moved in front of the camera and decided in real time (1550 nm lighting). A blue box means Wrapped, an orange box Non Wrapped, and the score is at the bottom right.

ROVI-SWIR test video (April 2026, 1550 nm) — inspection area (box), verdict and score. Film that is almost invisible in visible light shows up as a difference in brightness in SWIR
The print looking different from visible light is also typical of SWIR — many inks absorb less in SWIR and remain only as brightness, not colour. Decision accuracy depends on the product, lighting and installation, so it is evaluated in an on-site test.

9. Strengths and limits

Strengths

StrengthWhy
Sees differences in materialWater and plastics absorb in the SWIR band — same colour, different material, still distinguishable
Sees clear thingsClear film looks darker in its absorption band
Looks past print and dyeMany inks absorb less in SWIR, so what lies beneath shows
Handles hazeLonger wavelengths scatter less in haze and light fog than visible light
Simple decisionsWith the right wavelength, brightness alone can decide

Limits

LimitDetailsWhat to do
Price and resolutionInGaAs sensors are expensive and about 1.3 MPChoose lens magnification to give the needed resolution over the inspection area
No colourMono images — RGB suits colour and text inspection betterPair with an RGB camera when needed
Depends on lightingSees reflected light, not heat — light wavelength and strength decide the resultNarrow-band LED lighting, block outside light
Exposure and saturationWith the wrong exposure the difference disappears (1300 nm and below in the test)Per-wavelength exposure, fixed rather than automatic exposure
Sensitive to waterMoist targets look dark all overAdjust wavelength and inspection area
LensesOrdinary lenses may lose focus and transmission in SWIRSWIR-coated lenses

10. Where to use it

Selection guide

◎ best · ○ possible · △ limited · ✕ unsuitable

TaskSWIRRGBThermalWhy
Clear film or wrap present◎△△Film looks darker in its absorption band (ROVI-SWIR)
Moisture and dryness◎✕○Water absorbs at 1450 nm
Telling plastics apart◎△✕Each material absorbs at different wavelengths
Bruises and foreign matter in produce○○△Differences in moisture and tissue
Checking under print and labels○✕✕Inks absorb less in SWIR
Colour, text, appearance inspection△◎✕Colour is RGB territory
Temperature measurement✕✕◎Heat is thermal-camera territory

FLOYD's application

ROVI-SWIR is being commercialised first for deciding whether film-wrapped products such as cup noodles are wrapped (UX packaging, 2026), supplied through SI partners or directly to end customers.

11. Camera and ROVI-SWIR

LUCID Atlas SWIR 1.3MP

ItemDetails (spec)
ModelAtlas SWIR 1.3MP (ATP013S)
SensorSony IMX990 InGaAs (SenSWIR) · 1/2"
Resolution and pixel1280 × 1024 · 5 µm
Sensitivity400–1700 nm (mono)
Shutter and speedGlobal shutter · up to 84.9 fps
CoolingTEC (sensor cooling)
Interface and protectionGigE Vision · PoE+ · IP67
LensC-mount

ROVI-SWIR

ItemDetails
CameraLUCID SWIR camera (short-wave infrared)
Lighting1550 nm narrow-band LED
ProcessingEdge device · no AI training
UXHeadless device + companion app
OSWindows / Ubuntu 22.04
MaturityCommercialising — UX packaging and commercialisation (2026)

Send application review requests through floyd.kr contact.

12. Glossary

TermMeaning
SWIRShort-Wave Infrared. Light of about 1000–1700 nm (up to 2500 nm in the wider sense)
NIRNear Infrared. About 700–1000 nm
LWIR, thermalLong-Wave Infrared (8–14 µm). Sees the heat an object gives off
InGaAsIndium gallium arsenide. A semiconductor sensitive into SWIR — the material of SWIR sensors
Absorption bandA wavelength a material absorbs strongly — around 1450 nm for water, 1730 nm for plastics, and so on
Narrow-band lightingLED or filtered lighting that gives light around one wavelength only
SaturationThe image stuck at maximum brightness (255), so no difference can be seen
Inspection area (ROI)The part of the image used for the decision
ThresholdThe brightness boundary between film and no film
Separation d′How far apart the two brightness distributions are; higher means easier to tell apart
Global shutterCaptures all pixels at the same instant — moving products are not distorted
TECThermoelectric cooler. Cools the sensor to reduce noise