OCR Model

Class: OCRModelBlockV1

Source: inference.core.workflows.core_steps.models.foundation.ocr.v1.OCRModelBlockV1

Retrieve the characters in an image using DocTR Optical Character Recognition (OCR).

This block returns the text within an image.

You may want to use this block in combination with a detections-based block (i.e. ObjectDetectionBlock). An object detection model could isolate specific regions from an image (i.e. a shipping container ID in a logistics use case) for further processing. You can then use a DynamicCropBlock to crop the region of interest before running OCR.

Using a detections model then cropping detections allows you to isolate your analysis on particular regions of an image.

Type identifier

Use the following identifier in step "type" field: roboflow_core/ocr_model@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to OCR Model in version v1.

• inputs: Triangle Visualization, Morphological Transformation, Ellipse Visualization, SIFT, Blur Visualization, Stitch Images, Halo Visualization, Stability AI Outpainting, Camera Focus, Dynamic Crop, Model Comparison Visualization, Circle Visualization, Keypoint Visualization, Pixelate Visualization, Image Slicer, Color Visualization, Trace Visualization, Line Counter Visualization, Label Visualization, Icon Visualization, SIFT Comparison, Dot Visualization, QR Code Generator, Corner Visualization, Camera Focus, Image Slicer, Depth Estimation, Contrast Equalization, Grid Visualization, Text Display, Reference Path Visualization, Image Threshold, Perspective Correction, Image Contours, Bounding Box Visualization, Polygon Zone Visualization, Polygon Visualization, Background Subtraction, Background Color Visualization, Halo Visualization, Stability AI Inpainting, Image Convert Grayscale, Crop Visualization, Camera Calibration, Polygon Visualization, Image Blur, Relative Static Crop, Heatmap Visualization, Absolute Static Crop, Classification Label Visualization, Mask Visualization, Image Preprocessing, Stability AI Image Generation
• outputs: Triangle Visualization, Detections Stitch, Roboflow Dataset Upload, Detections Classes Replacement, Ellipse Visualization, Morphological Transformation, LMM, Cache Get, Florence-2 Model, CLIP Embedding Model, Blur Visualization, Anthropic Claude, Halo Visualization, Google Gemini, Llama 3.2 Vision, Model Comparison Visualization, Keypoint Visualization, Pixelate Visualization, Size Measurement, Line Counter, Stitch OCR Detections, Roboflow Dataset Upload, Line Counter Visualization, Label Visualization, QR Code Generator, SIFT Comparison, Distance Measurement, Email Notification, SAM 3, Slack Notification, Detections Stabilizer, Path Deviation, Florence-2 Model, Corner Visualization, SAM 3, Anthropic Claude, OpenAI, Detections Combine, Google Gemini, Perception Encoder Embedding Model, Bounding Box Visualization, Anthropic Claude, Pixel Color Count, Background Color Visualization, Polygon Visualization, Image Blur, Time in Zone, Clip Comparison, Detections Merge, Heatmap Visualization, CogVLM, Mask Visualization, Image Preprocessing, Byte Tracker, Twilio SMS Notification, PTZ Tracking (ONVIF).md), Instance Segmentation Model, OpenAI, Detections Transformation, Stability AI Outpainting, Moondream2, Stitch OCR Detections, Dynamic Crop, Model Monitoring Inference Aggregator, Circle Visualization, Detection Offset, Byte Tracker, Trace Visualization, OpenAI, Color Visualization, YOLO-World Model, Icon Visualization, Dot Visualization, Cache Set, Time in Zone, Email Notification, Velocity, Instance Segmentation Model, Path Deviation, Camera Focus, Twilio SMS/MMS Notification, Contrast Equalization, Depth Estimation, Segment Anything 2 Model, Roboflow Custom Metadata, Text Display, LMM For Classification, Detections Filter, Reference Path Visualization, Image Threshold, Perspective Correction, Polygon Zone Visualization, Detection Event Log, Local File Sink, Polygon Visualization, Halo Visualization, Byte Tracker, Google Vision OCR, SAM 3, Stability AI Inpainting, Time in Zone, Crop Visualization, Detections Consensus, Google Gemini, Detections List Roll-Up, Webhook Sink, Classification Label Visualization, Overlap Filter, OpenAI, Seg Preview, Line Counter, Stability AI Image Generation

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds OCR Model in version v1 has.

Bindings

• input

  • images (image): The image to infer on..

• output

  • result (string): String value.
  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.
  • parent_id (parent_id): Identifier of parent for step output.
  • root_parent_id (parent_id): Identifier of parent for step output.
  • prediction_type (prediction_type): String value with type of prediction.

Example JSON definition of step OCR Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/ocr_model@v1",
    "images": "$inputs.image"
}