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