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