Vision processing features that can be enabled or disabled.
using Nutrient;VisionFeatures is a flags enum: combine values with |.
Values
| Name | Value | Description |
|---|---|---|
VisionFeatures.Unknown | 0 | No features enabled. |
VisionFeatures.Equation | 1 | Mathematical equation detection and recognition. |
VisionFeatures.Table | 2 | Table structure detection and extraction. |
VisionFeatures.KeyValueRegion | 4 | Key-value region detection for form-like content. |
VisionFeatures.ImageClassification | 8 | Image classification for figures and diagrams. |
VisionFeatures.Handwriting | 16 | Image classification for figures and diagrams. |
VisionFeatures.Form | 32 | Form field detection (TextBox, ChoiceButton, Signature). |
VisionFeatures.BarcodeDetection | 64 | Barcode/QR decode-test on image regions: regions whose content decodes as a barcode are emitted as BarcodeNode instead of PictureNode. |
VisionFeatures.InlineStyles | 128 | Inline text-style classification (bold, italic, underline, strikeout, highlight, superscript, subscript) on OCR words. Advanced options are configured via InlineStyleSettings. |
VisionFeatures.Lexicon | 256 | Language-aware dehyphenation from lexicon packs; off means the built-in English lists only. |
VisionFeatures.All | 511 | All vision features enabled. |