# 🤟 Kenyan Sign Language Detection Application
A real-time Kenyan Sign Language (KSL) detection and translation system powered by Machine Learning, OpenCV, and MediaPipe Hand Landmarker.
The application detects Kenyan Sign Language gestures from a webcam feed, translates them into text in real time, converts text into speech, and supports text-to-sign translation using pre-recorded sign videos.
## 🚀 Features
* ✅ Real-time KSL gesture detection
* ✅ Live webcam prediction
* ✅ Sign-to-text translation
* ✅ Text-to-speech conversion
* ✅ Text-to-sign video translation
* ✅ MediaPipe Hand Landmarker integration
* ✅ Machine Learning gesture classification
* ✅ streamlit web application
* ✅ CPU optimized for low-powered laptops
---
## 🧠 Technologies Used
* Python 3.10+
* streamlit
* OpenCV
* MediaPipe Tasks API
* Scikit-learn
* XGBoost
* NumPy
* pyttsx3
Research and implementation were inspired by real-time sign language detection systems and pose-based gesture recognition pipelines. ([arXiv][1])
---
# 📂 Project Structure
```bash
kenya-sign-language-detection-app-application/
│
├── app.py
├── videos/
│ ├── agreement/
│ │ └── sign1.mp4
│ ├── good/
│ └── bad/
│
├── model_config.pkl
├── label_encoder.pkl
├── mean.pkl
├── std.pkl
├── hand_landmarker.task
├── requirements.txt
└── README.md
```
---
# ⚙️ Installation Guide
## 1️⃣ Clone Repository
```bash
git clone
github.com
```
Or visit:
Kenya Sign Language Detection Application Repository
---
## 2️⃣ Create Virtual Environment
### Windows
```bash
python -m venv venv
venv\Scripts\activate
```
### Linux / Mac
```bash
python3 -m venv venv
source venv/bin/activate
```
---
## 3️⃣ Install Dependencies
```bash
pip install -r requirements.txt
```
If `requirements.txt` is missing:
```bash
pip install streamlit
pip install opencv-python
pip install mediapipe
pip install numpy
pip install scikit-learn
pip install xgboo …