Cloudinary Blog
Build a Facial Emotion Recognition Based Video Suggestion App

Developers are always looking for new and creative ways to deliver content that resonates with the way users feel. Often using the latest technical innovations the market has to offer such as Artificial Intelligence (AI) and Machine Learning (ML). What better way to demonstrate innovative uses of these technology in a consumer market than capturing expressions from your users and then serving content based on that expression!

In this article we are going to build an app that suggests videos to users based on their facial expressions (i.e. emotion). To do this, we will use Cloudinary’s Advanced Facial Attributes Detection Add-on and the Cloudinary Video Player.

Webinar
Delivering Compelling Video Experiences at Scale

Set Up Cloudinary

Cloudinary makes adding image and video optimizations to applications a breeze. Head over to the Solutions Page to learn more about the features offered.

First, sign up for Cloudinary. Once you have created an account, you are able to use the “Advanced Facial Attributes Detection” add-on.

You can add the “Advanced Facial Attributes Detection” to your Cloudinary account here and follow the on-screen instructions.

Advanced Facial Attributes Detection Add-on

Make sure to note your API_KEY , API_SECRET and CLOUD_NAME from your developer console. This information is needed when integrating with your application.

Upload Images and Retrieve Facial Emotion Recognition from Images

Using Cloudinary to obtain the emotion from a facial image requires the Advanced Facial Attributes Detection Add-on when uploading the image. We add the adv_face as a tag to let Cloudinary know we are going to use the Advanced Facial Attributes Detection add-on to register the emotions from the detected users face.

When the image is successfully uploaded, emotions detected from the face and their confidence values are returned as part of the result. The emotion with the highest confidence is then selected.

JavaScript Sample:

Copy to clipboard
cloudinary.uploader.upload( req.body.image , function(result) {
  const emotions = result.info.detection.adv_face.data[0].attributes.emotion;
  let arr = JSON.parse(JSON.stringify(emotions));
  let visible_emotion = getMaxKey(arr); // this function gets the emotion with the highest confidence
  return res.json({
    status: true,
    emotion: visible_emotion
  })
},{ detection: "adv_face" });

You can then return the detected emotion to the frontend of your application.

Creating Video Playlists Based on emotion

Once the emotion is obtained on the front end, we want to display a set of videos to the user that correspond to the selected emotion. The Cloudinary Video Player makes creating playlists simple. You can create a video player and then populate it with videos from your media library that are tagged with the highest confidence emotion, such as ‘happiness’.

JavaScript Sample:

Copy to clipboard
let emotion = "happiness";
let cld = cloudinary.Cloudinary.new({ cloud_name: CLOUD_NAME, secure: true});b
// initialize video player
let demoplayer = cld.videoPlayer('elementID');
//  create playlist based on emotion
demoplayer.playlistByTag( emotion, { sourceParams: {angle:0}, autoAdvance: 0, repeat: true, presentUpcoming: 5});

Putting it all together, we have the sample of how it all works below:

Video Suggestion at Work

Conclusion

In this post, we have shown how to use the Advanced Facial Attributes Detection add-on from Cloudinary to create an application that enables us to serve videos to our users based on how they are feeling at the moment. We also leveraged the Cloudinary Video Player to serve the videos in a playlist format. You can learn more about using the video player and feel free to check out the github repository for the full source code. If you are up for the challenge, clone and submit your own Video Suggestion App below!


Further Reading on Video Manipulation

Recent Blog Posts

Transitioning JPEG-Based to JPEG XL-Based Images for Web Platforms

When the JPEG codec was being developed in the late 1980s, no standardized, lossy image-compression formats existed. JPEG became ready at exactly the right time in 1992, when the World Wide Web and digital cameras were about to become a thing. The introduction of HTML’s <img> tag in 1995 ensured the recognition of JPEG as the web format—at least for photographs. During the 1990s, digital cameras replaced analog ones and, given the limited memory capacities of that era, JPEG became the standard format for photography, especially for consumer-grade cameras.

Read more

Amplify Your Jamstack With Video

By Alex Patterson
Amplify Your Jamstack With Cloudinary Video

As defined by Amazon Web Services (AWS), Amplify is a set of products and tools with which mobile and front-end web developers can build and deploy AWS-powered, secure, and scalable full-stack apps. Also, you can efficiently configure their back ends, connect them to your app with just a few lines of code, and deploy static web apps in only three steps. Historically, because of their performance issues, managing images and videos is a daunting challenge for developers. Even though you can easily load media to an S3 bucket with AWS Amplify, transforming, compressing, and responsively delivering them is labor intensive and time consuming.

Read more
Cloudinary Helps Move James Hardie’s Experience Online

While COVID has affected most businesses, it has been particularly hard on those that sell products for the physical ‘brick and mortar’ world. One company that literally fits that bill is our Australian customer James Hardie, the largest global manufacturer of fibre cement products used in both domestic and commercial construction. These are materials that its buyers ideally want to see up close, in detail. When customers have questions, they expect personal service.

Read more
How to Build an Enhanced Gravatar Service, Part 2

Part 1 of this post defines the capabilities of an enhanced Gravatar service, which I named Clavatar, and describes the following initial steps for building it:

This post, part 2 of the series, explains how to make Clavatar work like Gravatar and to develop Clavatar’s capabilities of enabling requests for various versions of the images related to user accounts.

Read more