OCR Model

Class: OCRModelBlockV1

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

Retrieve the characters in an image using 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: Pixelate Visualization, Crop Visualization, Perspective Correction, Trace Visualization, Background Color Visualization, Line Counter Visualization, Keypoint Visualization, Reference Path Visualization, Color Visualization, Classification Label Visualization, Mask Visualization, Label Visualization, Dynamic Crop, Circle Visualization, Polygon Zone Visualization, Ellipse Visualization, Stability AI Image Generation, Triangle Visualization, SIFT, Image Slicer, Image Preprocessing, Bounding Box Visualization, Absolute Static Crop, Stitch Images, Image Blur, Image Slicer, Depth Estimation, Blur Visualization, Polygon Visualization, Camera Calibration, Image Threshold, Camera Focus, Image Contours, Corner Visualization, Model Comparison Visualization, Image Convert Grayscale, Relative Static Crop, Halo Visualization, SIFT Comparison, Stability AI Inpainting, Grid Visualization, Dot Visualization
• outputs: OpenAI, Twilio SMS Notification, LMM For Classification, Size Measurement, Crop Visualization, Llama 3.2 Vision, Trace Visualization, Pixel Color Count, Roboflow Dataset Upload, Perspective Correction, Background Color Visualization, LMM, Classification Label Visualization, Clip Comparison, Time in Zone, Path Deviation, Label Visualization, Stability AI Image Generation, Dynamic Crop, CogVLM, OpenAI, Cache Get, Cache Set, Polygon Visualization, Corner Visualization, YOLO-World Model, Model Comparison Visualization, Path Deviation, Instance Segmentation Model, Florence-2 Model, Instance Segmentation Model, Stability AI Inpainting, Time in Zone, Local File Sink, Distance Measurement, Model Monitoring Inference Aggregator, Google Gemini, Line Counter, Anthropic Claude, Line Counter Visualization, Keypoint Visualization, Email Notification, Reference Path Visualization, Florence-2 Model, Color Visualization, Mask Visualization, Roboflow Custom Metadata, Polygon Zone Visualization, Circle Visualization, Roboflow Dataset Upload, Ellipse Visualization, Triangle Visualization, Google Vision OCR, Segment Anything 2 Model, Image Preprocessing, Bounding Box Visualization, CLIP Embedding Model, Image Blur, Webhook Sink, Image Threshold, Slack Notification, Halo Visualization, SIFT Comparison, Detections Stitch, Line Counter, Dot 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.
  • 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"
}