Semantic analysis and processing based on understanding content.

Smartience 3.

The Smartience image processing library now in its third version. It can be optionally combined with Audiola for audio functionality.


  • Analysis of Faces and Objects:
    • face indexing by recognition.
    • detection of faces and objects of interest.
    • analyze for quality, e.g. blur, shake or contrast.
  • Processing:
    • Multi-layer processing and blending.
    • Bilateral filtering.
    • Image stitching, warping and remapping.
    • HDR image processing pipeline from sensor to display.
  • Metadata Generation:
    • Face feature descriptions, e.g. eyes, mouth, skin.
    • Active Shape Modeling (ASM) for accurate feature location.
    • scene descriptions, e.g. indoor, portrait, night, etc.
  • Content Picker:
    • auto-crop, auto pan and zoom, e.g. for 16:9 format.
    • create effective trailers, thumbs and music summaries.
  • Tools for advanced UI’s:
    • apply “Looks” with iterative refinement.
    • new interfaces for remote and touch UI’s.
    • auto-balancing of picture, dialog, music and effects.


Smartience is under continuous development with new features and capabilities added constantly. Please contact Uncut to discuss your requirements.