> For the complete documentation index, see [llms.txt](https://doc.faceplugin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.faceplugin.com/products/face-recognition-sdk/recognition/open-source-windows-and-linux/open-source-face-recognition-windows-sdk.md).

# Windows

Faceplugin open-source Face Recognition Windows SDK. Free on-premise Python sample. Lower accuracy than the commercial HTTP API on port 8083.

### Code <a href="#code" id="code"></a>

{% embed url="<https://github.com/Faceplugin-ltd/Open-Source-Face-Recognition-SDK>" %}
Free open-source Face Recognition Windows SDK
{% endembed %}

### Overview <a href="#overview" id="overview"></a>

Free **open-source** Face Recognition sample for Windows (Python). Detect faces, extract embeddings, and compare them **on your machine** — no Faceplugin cloud.

Accuracy is **lower** than the commercial [Face Recognition Windows SDK](/products/face-recognition-sdk/recognition/server-sdk/face-recognition-windows-sdk.md). Contact Faceplugin if you need the higher-accuracy native engine.

The Windows library path in `face_util/faceutil.py` should be:

```
dll_path = os.path.abspath(os.path.dirname(__file__)) + '/C/FaceUtil.dll'
```

### Setup <a href="#setup" id="setup"></a>

Please download anaconda on your computer and install it. We used Windows machine without GPU for testing

1. **Create anaconda environment**

   `conda create -n facesdk python=3.9`
2. **Activate env**

   `conda activate facesdk`
3. **Install dependencies**

   `pip install -r requirements.txt`
4. **Compare face images in the** `test` **directory**

   `python run.py`

### APIs and Parameters

* **GetImageInfo(image, faceMaxCount):** returns face bounding boxes, landmarks and feature embedding
* **get\_similarity(feat1, feat2):** returns similarity between two feature embeddings. 0 to 100
* **Threshold:** value to determine if two embeddings belong to same person, default = 75

### FAQ

**Same accuracy as the commercial API?** No. Use [Face Recognition Windows SDK](/products/face-recognition-sdk/recognition/server-sdk/face-recognition-windows-sdk.md) on port **8083** for the commercial engine.

### Related documentation

* [Faceplugin Face Recognition Server SDK](/products/face-recognition-sdk/recognition/server-sdk.md) · [Open Source Linux](/products/face-recognition-sdk/recognition/open-source-windows-and-linux/open-source-face-recognition-linux-sdk.md) · [Glossary](/help/resources/glossary.md)
* Lower accuracy than the commercial [Windows HTTP API](/products/face-recognition-sdk/recognition/server-sdk/face-recognition-windows-sdk.md).
* [Request a License](/help/request-a-license-and-support.md) · [Status codes](/help/resources/status-codes.md)
* [Combining products (eKYC)](/getting-started/choose-a-product.md) · [SDK comparison](/help/comparisons.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://doc.faceplugin.com/products/face-recognition-sdk/recognition/open-source-windows-and-linux/open-source-face-recognition-windows-sdk.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.