Face detection is one of the most common applications of Artificial Intelligence. The use of Facial detection has increased in the last couple of years.
Face-api.js has brought a JavaScript API for face detection and face recognition in the browser implemented on top of the tensorflow.js core API
In this tutorial, we will build the face recognition app that will work in the Browser. From the face, we will predict the Emotion, Gender, and age.
The output of this app will look as shown below.
Project Step
Step1 - Create a folder called face-recognition
Under the face-recognition
folder create the following folder structure
All folders are self-explanatory except models. That I will cover in going forward.
Step2 - download the face-api.min.js
Download the face-api.min.js
code from the following URL and paste it inside the js/face-api.min.js
file.
https://raw.githubusercontent.com/karkranikhil/face-recognition-using-js/master/js/face-api.min.js
Step3 - download the modal files
Models are the trained data that we will use to detect the feature from the face.
Download the files from the following URL and placed them inside the models
folder.
https://github.com/karkranikhil/face-recognition-using-js/tree/master/models
Step4 - Let's built the index.html
file.
In index.html
file we importing the style.css
for styles, face-api.min.js
for processing the model data and extracting the features and main.js where we will write our logic.
Inside the body
tag we are creating a video tag to get the face, result-container
for showing the emotion, gender, and age.
Place the below code inside the index.html
file
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta http-equiv="X-UA-Compatible" content="ie=edge" />
<title>Face recognition App</title>
<link rel="stylesheet" href="css/style.css" />
</head>
<body>
<header>Face recognition in the browser using Javascript</header>
<div class="container">
<video id="video" height="500" width="500" autoplay muted></video>
</div>
<div class="result-container">
<div id="emotion">Emotion</div>
<div id="gender">Gender</div>
<div id="age">Age</div>
</div>
<script src="./js/face-api.min.js"></script>
<script src="./js/main.js"></script>
</body>
</html>
Step5 - Let's built the main.js
file.
Inside the main.js
file we are using promise.all
to load the models to the face API. once the promise is resolved then we are calling the startVideo
method that starts the streaming. Below are the methods used for this demo
faceapi.detectSingleFace
method -detectSingleFace
utilize the SSD Mobilenet V1 Face Detector. You can specify the face detector by passing the corresponding options object. To detect the multiple faces replace thedetectSingleFace
withdetectAllFaces
withFaceLandmarks method
- It is used for Detecting 68 Face Landmark PointswithFaceExpressions method
- This method Detect all faces in an image + recognize facial expressions of each face and return the arraywithAgeAndGendermethod
- This method Detect all faces in an image + estimate age and recognize gender of each face and return the array
Replace the following code to the main.js
const video = document.getElementById("video");
const isScreenSmall = window.matchMedia("(max-width: 700px)");
let predictedAges = [];
/****Loading the model ****/
Promise.all([
faceapi.nets.tinyFaceDetector.loadFromUri("/models"),
faceapi.nets.faceLandmark68Net.loadFromUri("/models"),
faceapi.nets.faceRecognitionNet.loadFromUri("/models"),
faceapi.nets.faceExpressionNet.loadFromUri("/models"),
faceapi.nets.ageGenderNet.loadFromUri("/models")
]).then(startVideo);
function startVideo() {
navigator.getUserMedia(
{ video: {} },
stream => (video.srcObject = stream),
err => console.error(err)
);
}
/****Fixing the video with based on size size ****/
function screenResize(isScreenSmall) {
if (isScreenSmall.matches) {
video.style.width = "320px";
} else {
video.style.width = "500px";
}
}
screenResize(isScreenSmall);
isScreenSmall.addListener(screenResize);
/****Event Listeiner for the video****/
video.addEventListener("playing", () => {
const canvas = faceapi.createCanvasFromMedia(video);
let container = document.querySelector(".container");
container.append(canvas);
const displaySize = { width: video.width, height: video.height };
faceapi.matchDimensions(canvas, displaySize);
setInterval(async () => {
const detections = await faceapi
.detectSingleFace(video, new faceapi.TinyFaceDetectorOptions())
.withFaceLandmarks()
.withFaceExpressions()
.withAgeAndGender();
const resizedDetections = faceapi.resizeResults(detections, displaySize);
canvas.getContext("2d").clearRect(0, 0, canvas.width, canvas.height);
/****Drawing the detection box and landmarkes on canvas****/
faceapi.draw.drawDetections(canvas, resizedDetections);
faceapi.draw.drawFaceLandmarks(canvas, resizedDetections);
/****Setting values to the DOM****/
if (resizedDetections && Object.keys(resizedDetections).length > 0) {
const age = resizedDetections.age;
const interpolatedAge = interpolateAgePredictions(age);
const gender = resizedDetections.gender;
const expressions = resizedDetections.expressions;
const maxValue = Math.max(...Object.values(expressions));
const emotion = Object.keys(expressions).filter(
item => expressions[item] === maxValue
);
document.getElementById("age").innerText = `Age - ${interpolatedAge}`;
document.getElementById("gender").innerText = `Gender - ${gender}`;
document.getElementById("emotion").innerText = `Emotion - ${emotion[0]}`;
}
}, 10);
});
function interpolateAgePredictions(age) {
predictedAges = [age].concat(predictedAges).slice(0, 30);
const avgPredictedAge =
predictedAges.reduce((total, a) => total + a) / predictedAges.length;
return avgPredictedAge;
}
Step6 - Let's Add the style to the app.
Replace the style.css
with the following code.
body {
margin: 0;
padding: 0;
box-sizing: border-box;
height: 100vh;
background: #2f2f2f;
width: calc(100% - 33px);
}
canvas {
position: absolute;
}
.container {
display: flex;
width: 100%;
justify-content: center;
align-items: center;
}
.result-container {
display: flex;
width: 100%;
justify-content: center;
align-items: center;
flex-direction: column;
}
.result-container > div {
font-size: 1.3rem;
padding: 0.5rem;
margin: 5px 0;
color: white;
text-transform: capitalize;
}
#age {
background: #1e94be;
}
#emotion {
background: #8a1025;
}
#gender {
background: #62d8a5;
}
video {
width: 100%;
}
header {
background: #42a5f5;
color: white;
width: 100%;
font-size: 2rem;
padding: 1rem;
font-size: 2rem;
}
Step7 - Let's run the app by the live server or http-server
Once you run the app you will see the following output.
you can run the app deployed by me, using the following URL
https://face-recognition.karkranikhil.now.sh/
Reference
https://github.com/justadudewhohacks/face-api.js/
GITHUB - https://github.com/karkranikhil/face-recognition-using-js
Top comments (14)
Hi Nikhil,
As I am trying to host in local iis, I am getting 404 errors for files in console from js and model folders. I have enabled 'Static Content' from iis settings also. Is there any other configuration that i need to do?.
Please let me know. Your demo looks excellent, I would like to play with it if it can be configured on my system. Thanks.
-Janakiram
Salam Alaykum!
Could you please explain me how to create a web extension or software that hides website pictures by gender (for exemple if you choose female it hides all female pictures like that...)?
Thank you very much!
how to change color from pink to white face dot?
I wrote the following utility & library that uses face-api.js as well 🙂, nicely done: github.com/Risk3sixty-Labs/facerep...
I'll try it 👍
I don't see the camera even I turn it on.
can you check is there any error in the console.?
how do add the models folder into the code
What is the extension of models
age_gender_model-shard1
I am unable to host it on IIS
Face-api is too slow. Jeeliz FaceFilter is really faster (to run and to load), especially on mobile devices ( github.com/jeeliz/jeelizFaceFilter ).
Interesting..
Have created any model?
hi please, how will i download the modal files in step 3 from your github
download each file and paste inside the models folder.
Some comments may only be visible to logged-in visitors. Sign in to view all comments.