Glossary Updates12 new terms added to the glossaries · October 2, 2026, 22:44 CEST
AI TechDocKnowledge

Glossary · Machine vision

Dark-field illumination

Also known as: Dark-field lighting, Low-angle lighting

German: Dunkelfeldbeleuchtung

In machine vision, dark-field illumination is a lighting arrangement in which light strikes the object at a low angle so that directly reflected light misses the camera; flat surfaces appear dark and features that scatter light, such as scratches, edges or embossing, appear bright.

  • Machine vision

In one sentence

Dark-field illumination lights the object at a low angle so flat surfaces look dark and scratches, edges or embossing stand out bright.

Example

Dark-field illumination makes the dot-peened code on a steel part readable because the dots scatter light into the camera.

How it applies

  • Engineering: Low-angle ring lights and bar lights create dark-field conditions. The method highlights surface texture, scratches, dust and embossed or engraved features. Dome and coaxial lights, by contrast, produce bright-field conditions and hide much of this texture.
  • Commissioning: Working distance is critical because the light angle changes with height; parts must be presented at a consistent distance.
  • Documentation: The documentation team should document light type, height and angle, and make clear to maintenance staff that moving the light changes the result.

Dark-field vs. bright-field illumination

In Bright-field illumination, directly reflected light enters the camera and flat surfaces look bright. In dark-field, only scattered light enters and flat surfaces look dark. The choice depends on which features need contrast.

By knowledge.aitechdoc.world · Published September 26, 2026 · Last reviewed

Source: AI TechDoc Blog editorial definition, based on machine vision lighting practice

Definitions follow the cited standards and specifications. Where a source is a copyrighted publication, such as an ISO, IEC or EN standard, the definition is a close paraphrase, not a verbatim quotation, so as not to infringe copyright. We recommend reading the original publication. The sections “How it applies” are editorial commentary by AI TechDoc Blog and are not part of any standard.

Seen a mistake? Send us a note!