Overview

The OCR node allows for performing OCR (Optical Character Recognition) on objects within a Region of Interest (ROI), or on a ROI within the frame. This functionality is crucial for applications requiring text recognition and extraction from video feeds.

Properties

Property	Description	Type	Default	Required
roi_labels	Regions of interest labels	hidden		Yes
rois	Regions of interest. Type: polygon. Default: null. Conditional on `roi_labels`.	polygon	null	Yes
processing_mode	Processing mode. Options: ROIs, at an Interval (rois_interval), ROIs, upon a Trigger (rois_trigger), Objects in an ROI (objects).	enum	rois_interval	Yes
trigger	Queue ROI for OCR when this condition evaluates to true. Conditional on `processing_mode` being `rois_trigger`.	trigger-condition	null	Yes
objects_to_process	Object types to process. ex. `car`,`person`,`car.red`. Conditional on `processing_mode` being `objects`.	model-label	null	Yes
min_obj_size_pixels	Min. width and height of an object. Conditional on `processing_mode` being `objects`.	number	64	Yes
obj_lookup_size_change_threshold	Object size ratio change threshold. Slider min: 0.1, max: 2.0, step: 0.2. Conditional on `processing_mode` being `objects`.	slider	0.1	Yes
max_lookups_per_obj	Max. OCR attempts per object. Conditional on `processing_mode` being `objects`.	number	5	Yes
group_ocr_results	Group OCR texts?	bool	false	No
ocr_match_pattern	OCR match pattern. Only retain OCR results that match this Regular Expression pattern. Leave blank to keep unfiltered results.	string	null	No
min_confidence	OCR confidence threshold. Slider min: 0, max: 1, step: 0.05.	slider	0.7	Yes
additional_orientations	Comma separated string with additional orientations to consider for OCR. Valid orientation values: `90`, `180`, `270`. This is useful for recognizing text that is rotated at 90, 180, or 270 degrees.	enum-multi	null	No
ocr_interval	OCR lookups interval in seconds.	number	1	No
display_roi	Display ROI on video?	bool	true	No
display_objinfo	Display OCR info on video? Options: Disabled, Bottom left, Bottom right, Top left, Top right.	enum	bottom_left	No
debug	Log debugging information?	bool	false	No

Output Metadata

Metadata Property	Description
nodes.[node_id].rois.[roi_id].label_changed_delta	Indicates if there has been a change in the label of the ROI.
nodes.[node_id].rois.[roi_id].label_available	Indicates if a label is available for the ROI.
nodes.[node_id].recognized_obj_count	The count of recognized objects.
nodes.[node_id].recognized_obj_delta	The change in the count of recognized objects.
nodes.[node_id].label_changed_obj_delta	The change in the count of objects with changed labels.
nodes.[node_id].unrecognized_obj_count	The count of unrecognized objects.
nodes.[node_id].unrecognized_obj_delta	The change in the count of unrecognized objects.

{
  "nodes": {
    "[node_id]": {
      "rois": {
        "[roi_id]": {
          "label_changed_delta": true,
          "label_available": true
        }
      },
      "recognized_obj_count": 5,
      "recognized_obj_delta": 1,
      "label_changed_obj_delta": 2,
      "unrecognized_obj_count": 0,
      "unrecognized_obj_delta": 0
    }
  }
}

Example Usage

An example of how to use the OCR node in a video processing pipeline:

<VideoProcessingPipeline>
  <OCR
    roi_labels="['license_plate']"
    rois="[{ x: 10, y: 20, width: 100, height: 50 }]"
    processing_mode="objects"
    trigger="motion_detected"
    objects_to_process="['car']"
    min_obj_size_pixels={64}
    obj_lookup_size_change_threshold={0.3}
    max_lookups_per_obj={3}
    group_ocr_results={true}
    ocr_match_pattern="\d{3}-\d{2}"
    min_confidence={0.85}
    ocr_interval={5}
    display_roi={true}
    display_objinfo="bottom_left"
    debug={false}
  />
</VideoProcessingPipeline>