How to Capture Camera Stream with PHP and Perform Real-Time Emotion Recognition

1. Preparation

Install the PHP GD extension and V4L2 utilities on a Linux server to enable image processing and camera access.

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

2. Capture Video Stream

Use PHP's shell_exec to run an FFmpeg command that captures a single frame from /dev/video0 and saves it as an image.

<?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'>";
?>

3. Emotion Recognition

Integrate the open‑source Fer2013 model by invoking a Python script from PHP. Pass the captured image path to the script, which returns the predicted 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";
?>

Conclusion

The example demonstrates a simple end‑to‑end pipeline: capture a frame with PHP, run an AI model to classify the facial expression, and display both the image and the detected emotion on a web page.