Skip to content

OCRModel

Run Optical Character Recognition on a model.

Step parameters

  • type: must be OCRModel (required)
  • name: must be unique within all steps - used as identifier (required)
  • image: must be a reference to input of type InferenceImage or crops output from steps executing cropping ( Crop, AbsoluteStaticCrop, RelativeStaticCrop) (required)

Step outputs:

  • result - details of predictions
  • parent_id - identifier of parent image / associated detection that helps to identify predictions with RoI in case of multi-step pipelines
  • prediction_type - denoting ocr model