Liveness Detection: Sense

Welcome to Sense’s open source repository

This project serves an anti-spoofing detection API built using FastAPI. It analyzes facial images and predicts whether they are Real or Spoof using a set of trained models.

Quick Start

1. Prerequisites

[Docker](https://www.docker.com/products/docker-desktop) installed             

Clone the Repository

# Clone the repository
git clone https://github.com/sense-opensource/sense-liveness-checks.git

# Navigate into the project directory
cd sense-liveness-checks

🧠 Model

The anti spoof model file is not included in the repository. You must download the model file manually or programmatically and place it in the appropriate folder.

✅ Download Instructions

Download the model file from the below link:

https://github.com/sense-opensource/sense-liveness-checks/releases/download/v1.0.0/efficientnet-b7.onnx this file needs to be placed inside the resources/deepfake/ folder

Ensure the model is saved in: resources/deepfake/efficientnet-b7.onnx

2. API Configuration

Method 1: Install Python Dependencies

pip install -r requirements.txt

Start the FastAPI Server

uvicorn app:app --reload

This will start the API server on: http://localhost:3016

Method 2: Running with Docker

Build Docker Image

docker build -t sense_liveness_opensource_image .

Run Docker Container

docker run -d --name sense_liveness_opensource_container -p 3016:3016 sense_liveness_opensource_image

This will start the API server on: http://localhost:3016

3. Run the Frontend

cd front-end
npm install
npm run dev

By default, the frontend runs on : http://localhost:3010

Useful Docker Commands

Stop container

docker stop sense_liveness_opensource_container

Remove container

docker rm -f sense_liveness_opensource_container

Remove image

docker rmi -f  sense_liveness_opensource_image

View logs

docker logs anti_spoof_container

License

MIT License — free to use, share, and modify