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

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"
}