AI Image Object Detection, Cropping, and Indexing
detail.loadingPreview
Detect objects in an image, crop them, and index them for searchable metadata.
About This Workflow
This workflow leverages AI to analyze an image, identify specific objects within it, and then extracts these objects as individual image files. The extracted object images are then uploaded to Cloudinary and their metadata, including source image URL, detected object label, and cropped image URL, is indexed into Elasticsearch. This creates a foundation for an image search service that can query based on detected object associations.
Key Features
- Utilizes Cloudflare Workers AI for object detection.
- Dynamically crops identified objects from the source image.
- Uploads cropped images to Cloudinary for hosting.
- Indexes image metadata into Elasticsearch for searchability.
- Supports setting workflow variables for customization.
How To Use
- Set Variables: Configure essential variables like
CLOUDFLARE_ACCOUNT_ID,model(e.g.,@cf/facebook/detr-resnet-50),source_imageURL, andelasticsearch_indexin theSet Variablesnode. - Fetch Source Image: The workflow fetches the image specified in the
source_imagevariable. - Object Classification: The
Use Detr-Resnet-50 Object Classificationnode sends the image to the Cloudflare AI API to detect objects. - Filter Results: The
Split Out Results OnlyandFilter Score >= 0.9nodes process the AI output, keeping only detections with a confidence score of 0.9 or higher. - Crop Objects: For each high-confidence detection, the workflow fetches the source image again and uses the
Crop Object From Imagenode to extract the detected object based on its bounding box coordinates. - Upload to Cloudinary: The cropped object images are uploaded to Cloudinary using the
Upload to Cloudinarynode. - Index in Elasticsearch: The
Create Docs In Elasticsearchnode indexes the metadata, including URLs and detected labels, into the specified Elasticsearch index.
Apps Used
Workflow JSON
{
"id": "c2ff5826-cac8-4978-9743-fdd275ececbb",
"name": "AI Image Object Detection, Cropping, and Indexing",
"nodes": 18,
"category": "AI",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: c2ff5826-cac8...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
Generate Multilingual Image Captions and Overlay
This workflow generates captions for images using Google Gemini and overlays them onto the image, with support for multilingual output.
Build an AI Documentation Expert Chatbot with Gemini RAG
This n8n workflow automates the creation of an AI-powered expert chatbot capable of answering questions based on your documentation. It intelligently ingests, cleans, and processes your knowledge base, preparing it for a Retrieval Augmented Generation (RAG) pipeline with Google Gemini.
LangChain Workflow Retriever Example
Demonstrates using LangChain's Retriever QA Chain to query data retrieved from another workflow.