# Detect Unusual Crop Images

Source: https://openflow.run/en/templates/detect-unusual-crop-images/
Content language: en
Template revision: 6a810ce0d6451572951d8ffad4656467a01774f0

Research

Compare a crop image with prepared class centers and thresholds in Qdrant.

[Use in Open Flow](https://console.openflow.run/flows?importUrl=https%3A%2F%2Fraw.githubusercontent.com%2Foomol-lab%2Fawesome-workflow-templates%2F6a810ce0d6451572951d8ffad4656467a01774f0%2Fworkflows%2Fdetect-unusual-crop-images%2Ftemplates%2Fdetect-unusual-crop-images.openflow.json)

*   [Open Flow JSON](https://github.com/oomol-lab/awesome-workflow-templates/blob/6a810ce0d6451572951d8ffad4656467a01774f0/workflows/detect-unusual-crop-images/templates/detect-unusual-crop-images.openflow.json)
*   [n8n JSON](https://github.com/oomol-lab/awesome-workflow-templates/blob/6a810ce0d6451572951d8ffad4656467a01774f0/workflows/detect-unusual-crop-images/templates/detect-unusual-crop-images.n8n.json)

![Detect Unusual Crop Images workflow in Open Flow](https://openflow.run/template-previews/detect-unusual-crop-images/light.webp)

Compare a crop image with prepared class centers and thresholds in Qdrant.

## Setup and use

Prepare a Qdrant collection with the named vector **voyage**, one or more crop center points marked **is\_medoid**, and a numeric **is\_medoid\_cluster\_threshold** plus **crop\_name** on each center. The collection must use embeddings compatible with Voyage multimodal-3. Set the Qdrant host and collection in **Configure crop collection**, and configure the QDRANT\_API\_KEY and VOYAGE\_API\_KEY secrets.

The image URL is sent to Voyage. The collection and thresholds must already exist; this workflow does not create them.

## Behavior

The workflow counts crop classes, embeds the image and compares each returned center with its own threshold. It reports the highest-scoring qualifying crop or an undefined-crop alert. This is a similarity-based indication and should be reviewed before making decisions. An empty collection or missing thresholds requires configuration.

In n8n

In n8n configure the same collection in **Variables for medoids** and connect Qdrant and Voyage credentials. Run the Open Flow workflow with a publicly accessible HTTP image URL, or call the n8n sub-workflow with an input object containing query.imageURL.

Inspiration & credits

Adapted from [Anomaly detection tool (crops dataset)](https://github.com/enescingoz/awesome-n8n-templates/blob/827110332c21cbe000ab13f6d292d5adb1f1f8db/AI_Research_RAG_and_Data_Analysis/Automated%20Hugging%20Face%20Paper%20Summary%20Fetching%20%26%20Categorization%20Workflow.json) in [enescingoz/awesome-n8n-templates](https://github.com/enescingoz/awesome-n8n-templates).

Source collection notice: © 2024–2026 Enes Cingoz, [CC BY 4.0](https://github.com/enescingoz/awesome-n8n-templates/blob/827110332c21cbe000ab13f6d292d5adb1f1f8db/LICENSE). The source export does not identify a separate template author or license. See [repository licensing](https://github.com/oomol-lab/awesome-workflow-templates/blob/6a810ce0d6451572951d8ffad4656467a01774f0/README.md#licensing) for the scope of OOMOL contributions and third-party material.

## What you’ll need

*   Voyage AI API key
*   Qdrant collection with named voyage vectors, crop medoids and per-class thresholds

*   images
*   qdrant
*   voyage ai
*   classification

[View on GitHub](https://github.com/oomol-lab/awesome-workflow-templates/blob/6a810ce0d6451572951d8ffad4656467a01774f0/workflows/detect-unusual-crop-images/README.md)
