Machine Vision Resolution Guide

Spatial Resolution in Machine Vision: mm per Pixel, Minimum Detectable Size, and the Diffraction Limit

How field of view, pixel count, lens resolving power, and aperture combine to set the smallest feature a camera system can actually detect.

By Max Henkart, Commonlands · Updated May 2026 · 10 min read

A camera with a C-mount lens imaging a fine dot-grid calibration target on a metrology stage

Spatial resolution is the real-world size represented by one pixel at the working distance. Divide the field of view by the pixel count across it: a 100mm wide FOV on 2592 horizontal pixels gives 0.039mm per pixel. The smallest reliably detectable feature must span several pixels, typically 3 to 5 for detection and 10 or more for measurement.

Pixel math sets the ceiling, not the result. The lens must resolve the spatial frequency the pixel pitch demands (the Nyquist rule, lp/mm = 1 ÷ (2 × pixel pitch)), and the aperture must keep the diffraction Airy disk (d = 2.44 × λ × F/#) below roughly two pixel pitches. This guide covers all four layers: pixel math, angular resolution, lens resolving power, and diffraction.

What Is Spatial Resolution in Machine Vision?

Spatial resolution is the real-world size one pixel represents at the working distance, written as mm per pixel. Two numbers set it: the field of view and the pixel count across that dimension, so it is not an intrinsic camera property. A 12MP camera (4032 × 3024) on a 600mm wide tote has 0.149mm per pixel; on a 60mm connector it has 0.0149mm per pixel, ten times finer. The camera did not change, the field of view did.

If one pixel covers 0.1mm, a 0.05mm scratch is sub-pixel and usually lost unless its contrast is high; a 0.4mm scratch spans four pixels and is detectable. Its distance-independent counterpart is angular resolution, covered in the IFOV section. A megapixel count is only a pixel budget, so this guide also covers resolving power and diffraction, with Commonlands M12 and C-mount examples.

A machine vision camera fixed above a resolution chart of fine black line pairs
Spatial resolution is set by how many millimeters each pixel samples.

How Do You Calculate mm per Pixel?

Divide the field of view by the pixel count along the same axis. A 100mm wide scene on 2592 horizontal pixels gives 0.0386mm per pixel. The reciprocal, pixels per mm, tells you how many pixels cover each millimeter.

mm/pixel = FOV_width (mm) ÷ H_pixels px/mm = H_pixels ÷ FOV_width (mm) Example: 100 ÷ 2592 = 0.0386 mm/px, or 25.9 px/mm. The vertical axis uses the same formula with vertical values.

Use mm per pixel for inspection sizing. Use pixels per mm when comparing against lens specifications, because resolving power is quoted in line pairs per millimeter and one line pair needs two pixels to sample. Model any sensor, focal length, and working distance with the Commonlands FOV calculator. With noticeable distortion, the average does not hold at the frame edges.

What Is the Minimum Detectable Size in Machine Vision?

Minimum detectable size is the smallest feature a system reliably identifies. Multiply spatial resolution by the pixel coverage the task needs: minimum size = (FOV ÷ pixel count) × required pixels. Two pixels is the theoretical sampling floor, reachable only with near-perfect contrast. Noise, defocus, or motion blur erases it. Production inspection typically needs 3 to 5 pixels across a defect, and measurement 10 or more.

Task Pixels across feature Notes
Theoretical sampling floor 2 Depends on sub-pixel alignment and near-perfect contrast; not a design point
High-contrast presence/absence 3–5 Workable margin for a dark crack on a bright background under controlled lighting
Shape or orientation classification 5–10 Enough detail to separate circular from elongated features
Low-contrast or textured defects 8–15 More pixels accumulate enough signal above the noise floor
Dimensional measurement 10+ Sub-pixel algorithms refine to ~0.1–0.3 px, but only on well-resolved boundaries
Worked example

Target: detect a 0.2mm scratch with 5 pixels of coverage. Required spatial resolution = 0.2 ÷ 5 = 0.04 mm/pixel. On a 2448-pixel-wide sensor, the maximum horizontal FOV = 0.04 × 2448 = 98mm. Find the focal length that produces a 98mm FOV at your working distance.

Motion Blur Eats the Pixel Budget

A part moving at velocity v during exposure t smears the image by v × t. If that smear exceeds half a pixel at your spatial resolution, features near the minimum detectable size start disappearing.

Blur (mm) = velocity (mm/s) × exposure (s) Max exposure = (0.5 × mm/pixel) ÷ velocity Example: 200mm/s line speed at 0.049 mm/pixel → max exposure ≈ 120µs. Shorter exposures need brighter, often strobed, illumination.

What Is Angular Resolution (IFOV) in Machine Vision?

Angular resolution, or instantaneous field of view (IFOV), is the angle a single pixel subtends: IFOV = FOV ÷ pixel count. An 80° FOV across 3840 pixels gives 0.021° per pixel, or 48 pixels per degree. Multiplied by the working distance, that becomes the pixel footprint on the object. Its inverse, pixels per degree, is often more intuitive: how many pixels land on a target that spans a given angle.

IFOV (deg) = HFOV ÷ N_pixels IFOV (rad) ≈ pixel pitch (mm) ÷ EFL (mm) pixel footprint (mm) ≈ WD (mm) × IFOV (rad) The pitch ÷ EFL form applies to rectilinear lenses; for fisheye projections, use the measured FOV from the datasheet. Example: 3.45µm pitch on a 7mm lens gives 0.000493 rad ≈ 0.028° per pixel; at 500mm the footprint is about 0.25mm.
Lens Horizontal FOV IFOV at 3840 px Pixels per degree
CIL250 25mm telephoto M12 20° 0.005° 192

At fixed sensor resolution, wide coverage and fine angular sampling are in direct tension. Because contrast, noise, and blur are worse in production than on the bench, design for roughly 2× to 3× the theoretical minimum pixel count.

What Does a Megapixel Rating Mean on a Machine Vision Lens?

A megapixel rating on a lens names the sensor class it was designed to cover (a pixel pitch plus a format), not its optical resolving power. Resolving power is measured in line pairs per millimeter at the image plane, and the Nyquist rule sets the requirement: lp/mm = 1 ÷ (2 × pixel pitch in mm).

Required lp/mm = 1 ÷ (2 × pixel pitch in mm) Example: 3.45µm pixels → 0.00345mm → 1 ÷ (2 × 0.00345) ≈ 145 lp/mm. This is the floor; add margin for corner performance and aperture effects.
Pixel pitch Required lp/mm (Nyquist) Example sensors
5.0µm class100 lp/mmLarger-pixel global shutter sensors
3.45µm145 lp/mmSony Pregius IMX250, IMX264 (5MP), IMX253, IMX304 (12MP)
2.74µm182 lp/mmSony Pregius S IMX547 (5.1MP), IMX546 (8.1MP), IMX541 (20.4MP)
2.0µm250 lp/mmSony IMX678 (8MP, 1/1.8") and similar embedded sensors
1.55µm323 lp/mmHigh-density embedded and smartphone-class sensors

Coverage is the second, independent requirement: the lens image circle must be at least the sensor diagonal, or the corners vignette. Two checks decide a match, both required: resolving power at or above the Nyquist lp/mm, and image circle at or above the sensor diagonal. If either fails, the lens limits the system regardless of the megapixel labels.

What Is the Diffraction Limit in Machine Vision?

The diffraction limit is the minimum blur spot a lens can produce at a given aperture, set by the wave nature of light rather than manufacturing quality. Stopping down shrinks aberrations but grows the Airy disk linearly with f-number, so a smaller aperture eventually caps resolution no matter how well the lens is made.

The MTF of a diffraction-limited lens falls to zero at a cutoff frequency of 1 ÷ (λ × F/#). At 550nm and F/8, that cutoff is roughly 227 lp/mm. At F/16 it drops to 114 lp/mm, below the 145 lp/mm a 3.45µm sensor needs. "Diffraction-limited" is not a defect label. It means the lens is corrected well enough that diffraction, not residual aberration, decides image quality at that aperture.

What Is an Airy Disk?

The Airy disk is the bright central spot of the diffraction pattern formed when light from a point source passes through a circular aperture. The first dark ring bounds it, and about 84% of the pattern's energy falls inside that boundary (Hecht, Optics, 5th ed.). No lens design can focus light to a smaller spot at a given aperture and wavelength.

d = 2.44 × λ × F/# d = Airy disk diameter (same units as λ). λ = wavelength. F/# = f-number. At 550nm: F/4 → 5.4µm, F/8 → 10.7µm, F/16 → 21.5µm. In microscopy terms, NA ≈ 1 ÷ (2 × F/#) and the Rayleigh criterion puts the minimum resolvable separation at 0.61 × λ ÷ NA. See the numerical aperture guide.
F-number Airy disk at 550nm Spans on 3.45µm pixel Spans on 2.74µm pixel Spans on 1.55µm pixel
F/1.92.5µm0.7 px0.9 px1.6 px
F/2.83.8µm1.1 px1.4 px2.4 px
F/45.4µm1.6 px2.0 px3.5 px
F/5.67.5µm2.2 px2.7 px4.8 px
F/810.7µm3.1 px3.9 px6.9 px
F/1114.8µm4.3 px5.4 px9.5 px
F/1621.5µm6.2 px7.8 px13.9 px

Wavelength scales the disk linearly. At 850nm the Airy disk is about 55% larger than at 550nm for the same f-number, so NIR systems hit diffraction at wider apertures than visible-light systems. See the NIR imaging guide for wavelength-specific notes.

Pixel-Pitch Matching: When the Sensor Out-Resolves the Lens

Compare the Airy disk to twice the pixel pitch, the Nyquist span. Once it exceeds that, diffraction erases detail the sensor could otherwise capture. From the table, that crossover lands near F/5.6 for 3.45µm pixels, near F/4 for 2.74µm pixels, and below F/2.8 for 1.55µm pixels. A 20MP sensor with 2.74µm pixels beats a 12MP sensor at F/2.8, but by F/8 the two perform alike: high-resolution sensors give less aperture latitude.

Add light before stopping down

Opening from F/11 to F/5.6 admits roughly 4× the light and halves the Airy disk. Brighter or strobed light buys back the exposure lost to a stopped-down aperture; nothing buys back the contrast lost to diffraction. Pick the aperture from the depth of field your scene needs with the depth of field calculator, then confirm the Airy disk against twice the pixel pitch and check MTF at that aperture. The Commonlands f-number guide covers the full tradeoff.

Lens Examples Across the Resolution Range

These Commonlands lenses pair a verified part to each common resolution tier.

Lens Picks by Resolution Requirement

Resolution tier Recommended lens Mount F# Smallest pixel pitch supported Note
1–2MP entry inspection CIL028 2.6mm M12 See product page Not the binding constraint at 1–2MP Covers up to 6MP at 2.2µm, so resolving power is not the limit at 1–2MP. Pick the lowest-cost lens that covers your format.
5MP general purpose CIL059 6mm M12 F/1.7–F/5.6 See product page Fixed-aperture M12 variants chosen at purchase, not an adjustable iris. The F/1.7 build is rated 4–6MP; the F/4.0 build reaches 12MP as residual aberrations drop.
8–12MP inspection CIL160 16mm M12 F/1.9–F/5.6 See product page Fixed-aperture variants rated 12MP at F/2.8–F/4.0. The F/5.6 build drops to 8MP as diffraction grows.
8–12MP metrology CIL514 25mm C-mount F/2.8–F/16 3.45µm Adjustable iris. The Airy disk reaches two pixel pitches near F/5.6, the practical stop-down limit at 550nm.
8–12MP fine-pitch CIL535 35mm C-mount F/2.0–F/16 2.2µm Adjustable iris, rated for 2.2µm pixels at 12MP. At 550nm the Airy disk reaches two pixel pitches near F/3.3, the practical stop-down limit, so buy depth of field with working distance or focal length, not the iris.

For sensors above 12MP on formats larger than about 1.1 inch, fixed-focal C-mount FA lenses from Kowa, Fujinon, and Moritex are the established choices. The Commonlands M12 and C-mount optics above target the 1/4" to 1.1" formats these tiers cover. Size the field of view for any pick in the FOV calculator.

Focal length control: set the FOV and the mm per pixel

3mm M12 Low Distortion Lens

Low Distortion 3.0mm M12 Lens

$49.00

Download .STPView Product
6mm M12 Lenses S Mount Lens

Low Distortion 6mm M12 Lens

$49.00

Download .STPView Product
Wide Angle M12 Lens

Wide-Angle 4.5mm M12 Lens

$49.00

Download .STPView Product
5mm M12 Lens for IMX334

IR Corrected 4.4mm M12 Lens

$79.00

Download .STPView Product

Browse Large Format High Res

Aperture control: manage the diffraction tradeoff

4mm C-Mount Lens

4mm C-Mount Lens 1/1.8" 3MP

$119.00

CIL570-F2.0-CMANIR — 16 in stock

View Product
8mm C-Mount Lens Basler C11-0824-12M-P

8mm C-Mount Lens 1.1" 12MP

$249.00

CIL508-F2.4-CMANIR — 36 in stock

Download .STPView Product
12mm C-Mount Lens for 1.1" Cameras

12mm C-Mount Lens 1.1" 12MP

$249.00

CIL512-F2.8-CMANIR — 7 in stock

Download .STPView Product
16mm C-Mount Lens for Machine Vision

16mm C-Mount Lens 1.1" 12MP

$249.00

CIL513-F2.8-CMANIR — 4 in stock

Download .STPView Product

Browse C‑Mount Lenses: 4mm – 75 mm Industrial Machine Vision Optics

Looking into a C-mount lens iris stopped down to a small polygonal aperture
A very small aperture sets the diffraction limit on resolution.

Frequently Asked Questions

What is spatial resolution in machine vision?

Spatial resolution is the real-world size represented by one pixel at the working distance, expressed in mm per pixel. Divide the field of view by the pixel count across it: a 100mm FOV on 2592 horizontal pixels gives 0.039mm per pixel. It sets the theoretical floor for the smallest detectable feature.

What is the minimum detectable size in machine vision?

Minimum detectable size is the smallest feature a vision system reliably identifies. Multiply spatial resolution by the pixels required across the feature: (FOV ÷ pixel count) × required pixels. A 100mm FOV on 2048 pixels gives 0.049mm per pixel, so a 5-pixel detection target means features of 0.24mm or larger.

What is IFOV in a camera?

IFOV (instantaneous field of view) is the angle subtended by one pixel: IFOV = FOV ÷ pixel count. A camera with an 80° horizontal FOV and 3840 pixels has an IFOV of about 0.021° per pixel, or 48 pixels per degree. Multiply IFOV in radians by working distance to get the pixel footprint on the object.

What does megapixel mean for a machine vision lens?

A megapixel rating describes the sensor class a lens is designed to cover, a combination of pixel pitch and format, not its optical resolving power. Resolving power is measured in lp/mm. Two lenses with different megapixel labels can resolve identically in lp/mm. The higher label often just reflects a larger image circle for a bigger sensor at the same pixel pitch.

What is the diffraction limit in machine vision?

The diffraction limit is the minimum blur spot a lens can produce at a given aperture, set by the wave nature of light. A diffraction-limited lens at F/8 and 550nm cannot resolve beyond roughly 227 lp/mm, and its Airy disk spans 10.7µm, more than three pixels on a 3.45µm sensor.

Match a Lens to Your Resolution Requirement

Send us the defect size, working distance, and sensor. The Commonlands engineering team will work through the FOV, pixel coverage, lp/mm, and aperture numbers with you, or you can run the math yourself first.