> For the complete documentation index, see [llms.txt](https://sign-language-center.gitbook.io/tech/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sign-language-center.gitbook.io/tech/technology.md).

# Technology

Sign Language Center uses a machine learning model built around an **image classification** approach to recognize hand gestures.

| Aspect          | Detail                                            |
| --------------- | ------------------------------------------------- |
| Approach        | Image classification for hand-gesture recognition |
| Training time   | 1,000+ hours                                      |
| Training data   | 15,000+ hand-gesture photos                       |
| Data conditions | Varied angles and lighting conditions             |

## How it works

1. **Capture:** the camera captures a live video feed of the signer's hand or hands.
2. **Hand detection:** the system locates the hand in each frame and isolates it from the background.
3. **Gesture classification:** the trained model classifies the hand shape into a letter or word.
4. **Output:** the recognized sign is shown as text in real time and, in later missions, spoken aloud with AI voice generation.

## Recognition modes

* **One-hand recognition:** alphabet letters and simple words such as "I love you", "thank you" and "hello".
* **Two-hand recognition:** words that require both hands to express their meaning.

## Training data

The model was trained on photos of hand gestures captured from many angles and under different lighting conditions, so that it keeps working in real-world settings such as dim rooms, bright windows and different camera positions.

## AI learning agent

The learning agent compares a learner's sign with the expected gesture, detects errors and gives suggestions to correct them. It powers the structured lessons described in the Roadmap, from the alphabet to everyday words.

## AI voice generation

The final mission combines the two-hand translator with AI voice generation, so that recognized signs are turned into natural-sounding speech and signers can take part in spoken conversations.

## Design principles

* **Free:** accessible to everyone at no cost.
* **Compact:** runs from a simple camera without special hardware.
* **Convenient:** quick to open and use in everyday situations.


---

# 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://sign-language-center.gitbook.io/tech/technology.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.