Cloudinary Blog

Advanced Facial Attributes Detection for Image Transformation

Advanced Facial Attributes Detection for Image Transformation

Update - December 2015: The add-on described in this post is no longer available since ReKognition terminated their services. However, all features described here are still available via a different and even better add-on: Advanced Facial Attributes Detection

Face Detection is a great feature that enables the automatic modification of images according to the detected faces within an image, making it simple to intelligently crop, position, resize and transform your images appropriately.

Facial Attribute Detection takes the process even further and extracts meaningful advanced data about the face(s) in the image, including the exact location of facial features. This allows you even greater control over your image categorization, and to automatically use these details to smartly crop, position, rotate and overlay images based on the detected facial features.

Facial Attribute Detection lets you know more than just the location of a person's facial features. How are they posed in 3 dimensions? Is the person wearing glasses? Do they have their eyes closed? Mouth open? Have a mustache or beard? What is the person's race, age and gender? What emotion are they displaying? Are they smiling? How beautiful are they? Retrieving this information makes it a simple matter to automatically categorize and tag your collection of images.

Webinar
How to Optimize for Page Load Speed

All of this is made possible with the ReKognition add-on, which has been directly integrated within Cloudinary’s infrastructure, further extending Cloudinary’s built-in face detection to a robust Facial Attribute Detection feature. By simply setting the detection parameter to rekognition_face when calling Cloudinary's upload API, ReKognition is utilized to automatically extract detailed face attributes from the uploaded image.

Ruby:
Copy to clipboard
Cloudinary::Uploader.upload("woman.jpg", 
              :detection => "rekognition_face")
PHP:
Copy to clipboard
\Cloudinary\Uploader::upload("woman.jpg", 
              array(
               "detection" => "rekognition_face"));
Python:
Copy to clipboard
cloudinary.uploader.upload("woman.jpg", 
              detection = "rekognition_face")
Node.js:
Copy to clipboard
cloudinary.uploader.upload("woman.jpg", 
              function(result) {console.log(result); }, { detection: "rekognition_face" });
Java:
Copy to clipboard
cloudinary.uploader().upload("woman.jpg", 
              Cloudinary.asMap("detection", "rekognition_face"));

Original woman image

The example JSON snippet displayed from the example image above contains the result returned from the face ReKognition request, which includes very detailed information regarding the face that was automatically detected in the image.

Copy to clipboard
{"rekognition_face": 
 "status": "complete",
  "data": [
    {
      "boundingbox": {
        "tl": {"x": 231.45, "y": 102.52},
        "size": {"width": 240.77, "height": 240.77 }},
      "confidence": 1,
      "eye_left": {"x":309.6, "y": 190.1},
      "eye_right": {"x": 407.9, "y": 213.6},
      "nose": {"x": 199.1, "y": 204.0},
      
      
      
      "smile": 0.96,
      "glasses": 0.01,
      "sunglasses": 0.04,
      "beard": 0,
      "mustache": 0,
      "eye_closed": 0,
      "mouth_open_wide": 0.73,
      "beauty": 0.63531,
      "sex": 1
    }
  ]
}

You can also use Cloudinary's Admin API to apply ReKognition face detection to already uploaded images (based on their public IDs), and the face attributes that were previously extracted are also available using the Admin API's show resource details method.

Face detection based cropping

Based on the position of facial attributes detected by the ReKognition add-on, Cloudinary can crop your images to focus on the detected facial features, while providing a large set of image transformation and cropping options when using a Cloudinary delivery URL or calling Cloudinary's image API.

To focus an automatic crop on the detected faces, simply set the crop parameter to thumb, fill or crop and the gravity parameter to rek_faces (set gravity to rek_face for focusing on the single largest detected face in the image). The resulting images are dynamically generated on-the-fly and the result is delivered via a fast CDN.

Original photo

The following code sample generates a 150x150 thumbnail of the nice_coupleimage shown above, using multiple face detection based cropping.

Ruby:
Copy to clipboard
cl_image_tag("nice_couple.jpg", :gravity=>"rek_faces", :width=>150, :height=>150, :crop=>"thumb")
PHP v1:
Copy to clipboard
cl_image_tag("nice_couple.jpg", array("gravity"=>"rek_faces", "width"=>150, "height"=>150, "crop"=>"thumb"))
PHP v2:
Copy to clipboard
(new ImageTag('nice_couple.jpg'))
  ->resize(Resize::thumbnail()->width(150)->height(150)
    ->gravity(Gravity::focusOn(FocusOn::rekFaces())));
Python:
Copy to clipboard
CloudinaryImage("nice_couple.jpg").image(gravity="rek_faces", width=150, height=150, crop="thumb")
Node.js:
Copy to clipboard
cloudinary.image("nice_couple.jpg", {gravity: "rek_faces", width: 150, height: 150, crop: "thumb"})
Java:
Copy to clipboard
cloudinary.url().transformation(new Transformation().gravity("rek_faces").width(150).height(150).crop("thumb")).imageTag("nice_couple.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('nice_couple.jpg', {gravity: "rek_faces", width: 150, height: 150, crop: "thumb"}).toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("nice_couple.jpg", {gravity: "rek_faces", width: 150, height: 150, crop: "thumb"})
React:
Copy to clipboard
<Image publicId="nice_couple.jpg" >
  <Transformation gravity="rek_faces" width="150" height="150" crop="thumb" />
</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="nice_couple.jpg" >
  <cld-transformation gravity="rek_faces" width="150" height="150" crop="thumb" />
</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="nice_couple.jpg" >
  <cl-transformation gravity="rek_faces" width="150" height="150" crop="thumb">
  </cl-transformation>
</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.Transform(new Transformation().Gravity("rek_faces").Width(150).Height(150).Crop("thumb")).BuildImageTag("nice_couple.jpg")
Android:
Copy to clipboard
MediaManager.get().url().transformation(new Transformation().gravity("rek_faces").width(150).height(150).crop("thumb")).generate("nice_couple.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().setTransformation(CLDTransformation().setGravity("rek_faces").setWidth(150).setHeight(150).setCrop("thumb")).generate("nice_couple.jpg")!, cloudinary: cloudinary)
150x150 thumbnail of nice_couple.jpg

Eyes detection based cropping

Cloudinary can also dynamically crop your images based on the position of detected eyes. Simply set the gravity parameter to rek_eyes (g_rek_eyes for URLs) to center the image on the detected eyes. The example below delivers a 200x60 thumbnail centered on the eyes:

Ruby:
Copy to clipboard
cl_image_tag("woman.jpg", :gravity=>"rek_eyes", :width=>200, :height=>60, :crop=>"thumb")
PHP v1:
Copy to clipboard
cl_image_tag("woman.jpg", array("gravity"=>"rek_eyes", "width"=>200, "height"=>60, "crop"=>"thumb"))
PHP v2:
Copy to clipboard
(new ImageTag('woman.jpg'))
  ->resize(Resize::thumbnail()->width(200)->height(60)
    ->gravity(Gravity::focusOn(FocusOn::rekEyes())));
Python:
Copy to clipboard
CloudinaryImage("woman.jpg").image(gravity="rek_eyes", width=200, height=60, crop="thumb")
Node.js:
Copy to clipboard
cloudinary.image("woman.jpg", {gravity: "rek_eyes", width: 200, height: 60, crop: "thumb"})
Java:
Copy to clipboard
cloudinary.url().transformation(new Transformation().gravity("rek_eyes").width(200).height(60).crop("thumb")).imageTag("woman.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('woman.jpg', {gravity: "rek_eyes", width: 200, height: 60, crop: "thumb"}).toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("woman.jpg", {gravity: "rek_eyes", width: 200, height: 60, crop: "thumb"})
React:
Copy to clipboard
<Image publicId="woman.jpg" >
  <Transformation gravity="rek_eyes" width="200" height="60" crop="thumb" />
</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="woman.jpg" >
  <cld-transformation gravity="rek_eyes" width="200" height="60" crop="thumb" />
</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="woman.jpg" >
  <cl-transformation gravity="rek_eyes" width="200" height="60" crop="thumb">
  </cl-transformation>
</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.Transform(new Transformation().Gravity("rek_eyes").Width(200).Height(60).Crop("thumb")).BuildImageTag("woman.jpg")
Android:
Copy to clipboard
MediaManager.get().url().transformation(new Transformation().gravity("rek_eyes").width(200).height(60).crop("thumb")).generate("woman.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().setTransformation(CLDTransformation().setGravity("rek_eyes").setWidth(200).setHeight(60).setCrop("thumb")).generate("woman.jpg")!, cloudinary: cloudinary)
200x60 thumbnail centered on eyes

Facial overlays

Thanks to the detailed information on the position of facial attributes detected by ReKognition, Cloudinary can add overlays while taking into account the pose of the face, and automatically scale and rotate the overlay accordingly.

Ruby:
Copy to clipboard
cl_image_tag("HarlequinMask.jpg")
PHP v1:
Copy to clipboard
cl_image_tag("HarlequinMask.jpg")
PHP v2:
Copy to clipboard
(new ImageTag('HarlequinMask.jpg'));
Python:
Copy to clipboard
CloudinaryImage("HarlequinMask.jpg").image()
Node.js:
Copy to clipboard
cloudinary.image("HarlequinMask.jpg")
Java:
Copy to clipboard
cloudinary.url().imageTag("HarlequinMask.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('HarlequinMask.jpg').toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("HarlequinMask.jpg")
React:
Copy to clipboard
<Image publicId="HarlequinMask.jpg" >

</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="HarlequinMask.jpg" >

</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="HarlequinMask.jpg" >

</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.BuildImageTag("HarlequinMask.jpg")
Android:
Copy to clipboard
MediaManager.get().url().generate("HarlequinMask.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().generate("HarlequinMask.jpg")!, cloudinary: cloudinary)
Harlequin mask

For example, in order to automatically overlay the above image of a harlequin mask scaled to 160% relative to the detected eyes in the main image:

Ruby:
Copy to clipboard
cl_image_tag("woman.jpg", :flags=>"region_relative", :gravity=>"rek_eyes", :overlay=>"HarlequinMask", :width=>1.6, :crop=>"scale")
PHP v1:
Copy to clipboard
cl_image_tag("woman.jpg", array("flags"=>"region_relative", "gravity"=>"rek_eyes", "overlay"=>"HarlequinMask", "width"=>"1.6", "crop"=>"scale"))
PHP v2:
Copy to clipboard
(new ImageTag('woman.jpg'))
  ->overlay(
      Overlay::source(Source::image('HarlequinMask')
        ->transformation((new ImageTransformation())
          ->resize(Resize::scale()->width(1.6)->regionRelative())))
      ->position((new Position())
        ->gravity(Gravity::focusOn(FocusOn::rekEyes()))
  ));
Python:
Copy to clipboard
CloudinaryImage("woman.jpg").image(flags="region_relative", gravity="rek_eyes", overlay="HarlequinMask", width="1.6", crop="scale")
Node.js:
Copy to clipboard
cloudinary.image("woman.jpg", {flags: "region_relative", gravity: "rek_eyes", overlay: "HarlequinMask", width: "1.6", crop: "scale"})
Java:
Copy to clipboard
cloudinary.url().transformation(new Transformation().flags("region_relative").gravity("rek_eyes").overlay(new Layer().publicId("HarlequinMask")).width(1.6).crop("scale")).imageTag("woman.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('woman.jpg', {flags: "region_relative", gravity: "rek_eyes", overlay: new cloudinary.Layer().publicId("HarlequinMask"), width: "1.6", crop: "scale"}).toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("woman.jpg", {flags: "region_relative", gravity: "rek_eyes", overlay: new cloudinary.Layer().publicId("HarlequinMask"), width: "1.6", crop: "scale"})
React:
Copy to clipboard
<Image publicId="woman.jpg" >
  <Transformation flags="region_relative" gravity="rek_eyes" overlay="HarlequinMask" width="1.6" crop="scale" />
</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="woman.jpg" >
  <cld-transformation flags="region_relative" gravity="rek_eyes" :overlay="HarlequinMask" width="1.6" crop="scale" />
</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="woman.jpg" >
  <cl-transformation flags="region_relative" gravity="rek_eyes" overlay="HarlequinMask" width="1.6" crop="scale">
  </cl-transformation>
</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.Transform(new Transformation().Flags("region_relative").Gravity("rek_eyes").Overlay(new Layer().PublicId("HarlequinMask")).Width(1.6).Crop("scale")).BuildImageTag("woman.jpg")
Android:
Copy to clipboard
MediaManager.get().url().transformation(new Transformation().flags("region_relative").gravity("rek_eyes").overlay(new Layer().publicId("HarlequinMask")).width(1.6).crop("scale")).generate("woman.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().setTransformation(CLDTransformation().setFlags("region_relative").setGravity("rek_eyes").setOverlay("HarlequinMask").setWidth(1.6).setCrop("scale")).generate("woman.jpg")!, cloudinary: cloudinary)
Harlequin masked face

Heres another example, this time with glasses.

Ruby:
Copy to clipboard
cl_image_tag("glasses.jpg")
PHP v1:
Copy to clipboard
cl_image_tag("glasses.jpg")
PHP v2:
Copy to clipboard
(new ImageTag('glasses.jpg'));
Python:
Copy to clipboard
CloudinaryImage("glasses.jpg").image()
Node.js:
Copy to clipboard
cloudinary.image("glasses.jpg")
Java:
Copy to clipboard
cloudinary.url().imageTag("glasses.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('glasses.jpg').toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("glasses.jpg")
React:
Copy to clipboard
<Image publicId="glasses.jpg" >

</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="glasses.jpg" >

</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="glasses.jpg" >

</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.BuildImageTag("glasses.jpg")
Android:
Copy to clipboard
MediaManager.get().url().generate("glasses.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().generate("glasses.jpg")!, cloudinary: cloudinary)
Glasses

Overlaying the above image scaled to 150% relative to the detected eyes in the main image, which is then presented as a 200 pixel wide round thumbnail centered on the face:

Ruby:
Copy to clipboard
cl_image_tag("woman.jpg", :transformation=>[
  {:flags=>"region_relative", :gravity=>"rek_eyes", :overlay=>"glasses", :width=>1.5, :crop=>"scale"},
  {:width=>200, :gravity=>"face", :radius=>"max", :crop=>"thumb"}
  ])
PHP v1:
Copy to clipboard
cl_image_tag("woman.jpg", array("transformation"=>array(
  array("flags"=>"region_relative", "gravity"=>"rek_eyes", "overlay"=>"glasses", "width"=>"1.5", "crop"=>"scale"),
  array("width"=>200, "gravity"=>"face", "radius"=>"max", "crop"=>"thumb")
  )))
PHP v2:
Copy to clipboard
(new ImageTag('woman.jpg'))
  ->overlay(
      Overlay::source(Source::image('glasses')
        ->transformation((new ImageTransformation())
          ->resize(Resize::scale()->width(1.5)->regionRelative())))
      ->position((new Position())
        ->gravity(Gravity::focusOn(FocusOn::rekEyes()))))
    ->resize(Resize::thumbnail()->width(200)->gravity(Gravity::focusOn(FocusOn::face())))
    ->roundCorners(RoundCorners::max());
Python:
Copy to clipboard
CloudinaryImage("woman.jpg").image(transformation=[
  {'flags': "region_relative", 'gravity': "rek_eyes", 'overlay': "glasses", 'width': "1.5", 'crop': "scale"},
  {'width': 200, 'gravity': "face", 'radius': "max", 'crop': "thumb"}
  ])
Node.js:
Copy to clipboard
cloudinary.image("woman.jpg", {transformation: [
  {flags: "region_relative", gravity: "rek_eyes", overlay: "glasses", width: "1.5", crop: "scale"},
  {width: 200, gravity: "face", radius: "max", crop: "thumb"}
  ]})
Java:
Copy to clipboard
cloudinary.url().transformation(new Transformation()
  .flags("region_relative").gravity("rek_eyes").overlay(new Layer().publicId("glasses")).width(1.5).crop("scale").chain()
  .width(200).gravity("face").radius("max").crop("thumb")).imageTag("woman.jpg");
JS:
Copy to clipboard
cloudinary.imageTag('woman.jpg', {transformation: [
  {flags: "region_relative", gravity: "rek_eyes", overlay: new cloudinary.Layer().publicId("glasses"), width: "1.5", crop: "scale"},
  {width: 200, gravity: "face", radius: "max", crop: "thumb"}
  ]}).toHtml();
jQuery:
Copy to clipboard
$.cloudinary.image("woman.jpg", {transformation: [
  {flags: "region_relative", gravity: "rek_eyes", overlay: new cloudinary.Layer().publicId("glasses"), width: "1.5", crop: "scale"},
  {width: 200, gravity: "face", radius: "max", crop: "thumb"}
  ]})
React:
Copy to clipboard
<Image publicId="woman.jpg" >
  <Transformation flags="region_relative" gravity="rek_eyes" overlay="glasses" width="1.5" crop="scale" />
  <Transformation width="200" gravity="face" radius="max" crop="thumb" />
</Image>
Vue.js:
Copy to clipboard
<cld-image publicId="woman.jpg" >
  <cld-transformation flags="region_relative" gravity="rek_eyes" :overlay="glasses" width="1.5" crop="scale" />
  <cld-transformation width="200" gravity="face" radius="max" crop="thumb" />
</cld-image>
Angular:
Copy to clipboard
<cl-image public-id="woman.jpg" >
  <cl-transformation flags="region_relative" gravity="rek_eyes" overlay="glasses" width="1.5" crop="scale">
  </cl-transformation>
  <cl-transformation width="200" gravity="face" radius="max" crop="thumb">
  </cl-transformation>
</cl-image>
.NET:
Copy to clipboard
cloudinary.Api.UrlImgUp.Transform(new Transformation()
  .Flags("region_relative").Gravity("rek_eyes").Overlay(new Layer().PublicId("glasses")).Width(1.5).Crop("scale").Chain()
  .Width(200).Gravity("face").Radius("max").Crop("thumb")).BuildImageTag("woman.jpg")
Android:
Copy to clipboard
MediaManager.get().url().transformation(new Transformation()
  .flags("region_relative").gravity("rek_eyes").overlay(new Layer().publicId("glasses")).width(1.5).crop("scale").chain()
  .width(200).gravity("face").radius("max").crop("thumb")).generate("woman.jpg");
iOS:
Copy to clipboard
imageView.cldSetImage(cloudinary.createUrl().setTransformation(CLDTransformation()
  .setFlags("region_relative").setGravity("rek_eyes").setOverlay("glasses").setWidth(1.5).setCrop("scale").chain()
  .setWidth(200).setGravity("face").setRadius("max").setCrop("thumb")).generate("woman.jpg")!, cloudinary: cloudinary)
Glasses overlayed on eyes

Summary

The ReKognition add-on is utilized to automatically extract detailed face attributes from your images, and enables advanced image manipulation and categorization based on the detected facial data, with relative scaling and rotation of overlays achieved automatically.

ReKognition detect face attributes add-on

The ReKognition add-on is available to all our free and paid plans. If you don't have a Cloudinary account, you are welcome to sign up to our free account and try it out.

Update - December 2015: The add-on described in this post is no longer available since ReKognition terminated their services. However, all features described here are still available via a different and even better add-on: Advanced Facial Attributes Detection

Recent Blog Posts

Create Lightweight Sites With Low-Code and No-Code Technology

Consumers expect modern websites to be mainly visual. But, the more compelling and complex the related media is, the more data is involved, compounding the site’s weight. In today’s content-craving world, delivering unoptimized media can cost you because it leads to sluggish page loads, resulting in visitors abandoning your site in search of a faster alternative. In fact, a page load that takes more than three seconds can cause as many as 40% of your visitors to bounce. Given this competitive, digital-first environment, you can’t afford to lose page views, for time is of the essence.

Read more
A Blueprint for AWS-Secured Webhook Listeners for Cloudinary

tl;dr: An AWS-secured and optimized Cloudinary webhook listener for extending the Cloudinary service

Code: Github

A webhook is a communication medium for sending notifications from one platform to another about events that occurred. In place are user-defined HTTP callbacks that are triggered by specific events. When a triggered event takes place on the source site, the webhook listens to the event, collects the data, and sends it to the URL you specified in the form of an HTTP request.

Read more
New Accessibility Features for Cloudinary’s Product Gallery Widget

Cloudinary’s Product Gallery widget, which launched in 2019, has enabled many brands to effectively and efficiently showcase their products in a sleek and captivating manner, saving countless hours of development time and accelerating release cycles. By adding Cloudinary’s Product Gallery widget with its customizable UI to their product page, retailers reap numerous benefits, often turning visitors into customers in short order.

Read more
Why Successful Businesses Engage With and Convert Audiences With Visual Media

Most business buyers prefer to research purchase options online, as do many shoppers. No wonder online retail sales in the U.S. rose by 32.4% in 2020—an impressive gain of $105 billion.

For B2B and B2C businesses, text-heavy websites are no longer adequate in attracting shoppers. Instead, engaging visual media—spin images, videos, 3D models, augmented reality—are becoming a must for conveying eye-catching details and differentiators about products or services.

Read more
Making User-Generated Content (UGC) Shoppable With Cloudinary

User-generated content (UGC) is a powerful marketing tool. Not only does video complement marketing efforts for e-commerce by enabling customers to explore products in greater detail, but UGC also adds an element of trust. As a bonus, user-generated video is an exceptional opportunity for e-businesses to attract website traffic without their marketing team having to create promotional videos from scratch. User-generated content drives conversions and brand loyalty as a direct result of authentic interaction.

Read more