FaceSDK - Linux

Face Recognition Linux Server SDK

Our SDK is fully on-premise, processing all happens on hosting server and no data leaves your server.

Installation

Prerequisites

Python 3.6+
Linux
CPU: 2 cores or more
RAM: 8GB or more

Installation Steps

Download the Face Recognition Linux Server Installer
Download the Server installer for your operating system from the following link:
Download the On-premise Server Installer
Install the On-premise Server
Run the installer and follow the on-screen instructions to complete the installation. Go to the Download folder and run this command.

$ cd Download
$ sudo dpkg -i --force-overwrite MiniAiLive-FaceSDK-LinuxServer.deb

Request License and Update You can generate the License Request file by using this command:

$ cd /opt/miniai/face-rec-service
$ sudo ./MiRequest request /home/ubuntu/Download/trial_key.miq

Then you can see the license request file on your directory, and send it to us via email or WhatsApp. We will send the license based on your Unique Request file, then you can upload the license file to allow to use. Refer the below images.

$ sudo ./MiRequest update /home/ubuntu/Download/trial_30.mis

Verify Installation After installation, verify that the On-premise Server is correctly installed by using this command:

$ systemctl list-units --state running

If you can see 'Mini-facesvc.service', 'Mini-fdsvc.service', the server has been installed successfully. Refer the below image.

API Reference

Endpoint

POST http://127.0.0.1:8083/api/face_detect <Face Detection, Face Attributes API>

Form Data:
- image: The image file (PNG, JPG, etc.) to be analyzed. This should be provided as a file upload

POST http://127.0.0.1:8083/api/face_detect_base64 <Face Detection, Face Attributes API>

Raw Data:

JSON Format:

{
    "image": "--base64 image data here--"
}

Other available endpoints here.

POST http://127.0.0.1:8083/api/face_match <1:1, 1:N Face Matching API>

POST http://127.0.0.1:8083/api/face_match_base64 <1:1, 1:N Face Matching API>

Response

The API returns a JSON object with the recognized details from the input face image. Here is an example response

Testing API

Gradio Demo

We have included a Gradio demo to showcase the capabilities of our Face Recognition SDK. Gradio is a Python library that allows you to quickly create user interfaces for machine learning models.

How to Run the Gradio Demo

Install Gradio:

First, you need to install Gradio. You can do this using pip:

git clone https://github.com/MiniAiLive/FaceRecognition-Windows.git
pip install -r requirement.txt
cd gradio

Run Gradio Demo:
```
python app.py
```

Python Test API Example

To help you get started with using the API, here is a comprehensive example of how to interact with the Face Recognition API using Python. You can use API with another language you want to use like C++, C#, Ruby, Java, Javascript, and more

Prerequisites

Python 3.6+
requests library (you can install it using pip install requests)

Example Script

This example demonstrates how to send an image file to the API endpoint and process the response.

import requests

# URL of the web API endpoint
url = 'http://127.0.0.1:8083/api/face_detect'

# Path to the image file you want to send
image_path = './test_image.jpg'

# Read the image file and send it as form data
files = {'image': open(image_path, 'rb')}

try:
    # Send POST request
    response = requests.post(url, files=files)

    # Check if the request was successful
    if response.status_code == 200:
        print('Request was successful!')
        # Parse the JSON response
        response_data = response.json()
        print('Response Data:', response_data)
    else:
        print('Request failed with status code:', response.status_code)
        print('Response content:', response.text)

except requests.exceptions.RequestException as e:
    print('An error occurred:', e)