Emotion Recognition Using PHP and Camera: A Step-by-Step Guide

Camera-based emotion recognition is introduced, explaining how to set up the environment on a Linux system using PHP.

First, install the PHP GD library and V4L2 utilities:

sudo apt-get install php7.4-gd
sudo apt-get install v4l-utils

Then, obtain a video frame from the camera using PHP's shell_exec to run an FFmpeg command, saving the image to a file and displaying it with an <img> tag.

<?php
function getVideoStream() {
    $cmd = "ffmpeg -i /dev/video0 -vf fps=1 -s 1280x720 -f image2 -frames 1 /path/to/image.jpg";
    shell_exec($cmd);
    return "/path/to/image.jpg";
}
$videoStream = getVideoStream();
echo "<img src='$videoStream'>";
?>

For emotion analysis, the Fer2013 model is invoked via a Python script. A PHP function getEmotion passes the image path to the script and returns the detected emotion.

<?php
function getEmotion($imagePath) {
    $modelPath = "path/to/Fer2013/model.hdf5";
    $cmd = "python3 scripts/emotion_classification.py $modelPath $imagePath";
    $emotion = shell_exec($cmd);
    return $emotion;
}
$emotion = getEmotion($videoStream);
echo "Current emotion: $emotion";
?>

Running the complete example displays the live camera frame on a web page and prints the inferred emotional state, providing a practical introduction to integrating camera input with AI-driven emotion detection in PHP.