region-extract — Traditional AI Model

Details

• CategoryTraditional
• Year-1
• License

Inputs & Outputs

Region DataInput · string

Region data JSON from an OCR node's Region Data output

TextOutput · string

One region per line; a region with no usable geometry is an empty line, so lines stay aligned with the OCR text

Parameters

use_bounding_boxboolean · default false

Output bounding boxes instead of polygons

When false (default), each line is the region's 4-point polygon as 'x1,y1,x2,y2,x3,y3,x4,y4'. When true, each line is the axis-aligned bounding box as 'xmin,ymin,xmax,ymax' — the Left,Top,Right,Bottom form the crop and mask by-coordinate nodes read.

Tags

• text
• ocr
• region
• polygon
• bounding-box
• extract

Alternatives in Text Tools

• Draw Text

  Overlay text on an image with font/size/color control.

• Text Concatenate

  Concatenate up to 4 text inputs into one output.

• Text Decorator

  Wrap text with a template (placeholder substitution).