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

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"
}