EasyOCR¶
Class: EasyOCRBlockV1
Source: inference.core.workflows.core_steps.models.foundation.easy_ocr.v1.EasyOCRBlockV1
Retrieve the characters in an image using EasyOCR 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.
Note that EasyOCR has limitations running within containers on Apple Silicon.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/easy_ocr@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Unique name of step in workflows. | ❌ |
language |
str |
Language model to use for OCR. | ❌ |
quantize |
bool |
Quantized models are smaller and faster, but may be less accurate and won't work correctly on all hardware.. | ❌ |
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 EasyOCR in version v1.
- inputs:
Icon Visualization,Stability AI Inpainting,Triangle Visualization,Background Color Visualization,Depth Estimation,Label Visualization,Model Comparison Visualization,Dot Visualization,Image Blur,Camera Calibration,Polygon Zone Visualization,SIFT,Stitch Images,Trace Visualization,Contrast Equalization,Morphological Transformation,Corner Visualization,Perspective Correction,Halo Visualization,Stability AI Image Generation,Reference Path Visualization,Relative Static Crop,Dynamic Crop,Line Counter Visualization,Image Slicer,Image Threshold,Keypoint Visualization,Absolute Static Crop,Heatmap Visualization,Blur Visualization,Circle Visualization,Text Display,Camera Focus,Crop Visualization,Grid Visualization,Classification Label Visualization,Polygon Visualization,Camera Focus,Polygon Visualization,Image Slicer,Image Preprocessing,Color Visualization,SIFT Comparison,Bounding Box Visualization,Image Contours,Halo Visualization,Stability AI Outpainting,Background Subtraction,Image Convert Grayscale,QR Code Generator,Pixelate Visualization,Ellipse Visualization,Mask Visualization - outputs:
Icon Visualization,Moondream2,Slack Notification,Label Visualization,Instance Segmentation Model,Dot Visualization,Trace Visualization,SAM 3,Time in Zone,Roboflow Custom Metadata,Semantic Segmentation Model,Image Threshold,Keypoint Visualization,PTZ Tracking (ONVIF),Overlap Filter,Single-Label Classification Model,Path Deviation,Blur Visualization,Circle Visualization,Crop Visualization,Email Notification,Classification Label Visualization,OpenAI,Detections Merge,OpenAI,Google Gemini,Twilio SMS Notification,YOLO-World Model,Twilio SMS/MMS Notification,Model Monitoring Inference Aggregator,Anthropic Claude,Path Deviation,Google Gemini,Time in Zone,Detections Filter,Distance Measurement,Stability AI Inpainting,S3 Sink,Depth Estimation,Model Comparison Visualization,Byte Tracker,SAM2 Video Tracker,Google Gemini,Detections Classes Replacement,Detections List Roll-Up,CLIP Embedding Model,Florence-2 Model,Size Measurement,LMM,Dynamic Crop,Detection Offset,SAM 3,Perception Encoder Embedding Model,Detections Stabilizer,Byte Tracker,Polygon Visualization,Mask Visualization,Webhook Sink,Seg Preview,SORT Tracker,OC-SORT Tracker,Detection Event Log,Object Detection Model,GLM-OCR,Roboflow Dataset Upload,Polygon Zone Visualization,Detections Stitch,Morphological Transformation,Instance Segmentation Model,Perspective Correction,Detections Combine,Cache Get,Anthropic Claude,Cache Set,Email Notification,SAM 3,Polygon Visualization,OpenAI,Stitch OCR Detections,Color Visualization,Local File Sink,Line Counter,Byte Tracker,Mask Area Measurement,Roboflow Vision Events,OpenAI,Llama 3.2 Vision,Clip Comparison,Instance Segmentation Model,Time in Zone,Triangle Visualization,LMM For Classification,Pixel Color Count,Background Color Visualization,Stitch OCR Detections,Line Counter,CogVLM,Anthropic Claude,Image Blur,Contrast Equalization,Corner Visualization,Velocity,Stability AI Image Generation,Halo Visualization,Detections Consensus,Reference Path Visualization,Line Counter Visualization,Multi-Label Classification Model,ByteTrack Tracker,Keypoint Detection Model,Roboflow Dataset Upload,Heatmap Visualization,Text Display,Segment Anything 2 Model,Camera Focus,Detections Transformation,Image Preprocessing,SIFT Comparison,Bounding Box Visualization,Stability AI Outpainting,Halo Visualization,QR Code Generator,Pixelate Visualization,Google Vision OCR,Ellipse Visualization,Florence-2 Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
EasyOCR 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 EasyOCR in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/easy_ocr@v1",
"images": "$inputs.image",
"language": "<block_does_not_provide_example>",
"quantize": "<block_does_not_provide_example>"
}