Cloudinary Blog

Face detection based cropping


Cloudinary’s roots go back to when we needed to embed users’ uploaded images and profile pictures for web projects we’ve developed.

We had to show people and faces of users in various dimensions and perspectives, and the process proved cumbersome.

These days, Cloudinary allows you to easily resize and crop your images to snugly fit the graphics design. But sometimes, just resizing pictures using ‘fill’ crop and ‘center’ gravity just doesn’t cut it. This is a common problem with user profile photos.

 

So we thought it is about time we add some more brainpower into the cropping process. Of-course we could just let the users manually crop their own profile pictures, but that just wasn’t fun enough :)

We decided to add face detection based cropping. Facebook use it internally to find faces of users and crop the profile pictures accordingly. Google does it as well. What about the rest of us?

Fortunately, we didn’t need to invent the wheel. Some top-notch face detection open source algorithms are freely available today. They are just not production ready or easy to integrate. The good news - we did the heavy lifting for you. We integrated existing tools and libraries, optimized their settings and added smart face detection based cropping to Cloudinary. Try it out - you won’t believe the difference that it makes.

Cloudinary supports either a single face detection or multiple faces detection (i.e., focusing on the people in a picture). You can easily create a face thumbnail of your users, crop an image to focus on a person or resize an image to fill the required dimensions while making sure the person in the original picture appears in the resized version of the image. And as usual, Cloudinary does all this automatically for you in the cloud and delivers the images through a fast CDN.

 

 

Using face detection based cropping with Cloudinary is very simple. Below are examples showing both cropping via our universal dynamic URLs and our Ruby on Rails integration.

http://res.cloudinary.com/demo/image/upload/w_100,h_100,c_thumb,g_face/face_top.jpg

<%= cl_image_tag("face_top.jpg", :width =>100, :height => 100,
:crop => :thumb, :gravity => :face) %>

For more details and usage examples, take a look at our documentation: http://cloudinary.com/documentation/image_transformations#face_detection

This feature is now available across all our plans, including the free one. We hope you like it.

 

Recent Blog Posts

Introducing Website Speed Test: An Image Analysis Tool Integrated with WebPagetest

Because images dominate page weight, methodical image optimization can have a significant effect on conversions and user experience. And the performance tools you choose to use can have a powerful impact on how websites are built and maintained. One such popular open source tool is WebPagetest. It is designed to measure and analyze webpage performance, which is why Cloudinary chose to partner with our friends over there to launch Website Speed Test.

Read more

You might have read some tutorials or articles explaining the importance of images and how to optimize them to deliver a great experience to your users. But does this work really translate into wins for your company? In this talk, you see real-world examples of the positive impact that image optimizations can have on metrics that your bosses and clients care about. You will walk away from this talk with compelling data and useful tools to help you get buy-in and support for this important user experience work at your company.

Read more
Don’t let your digital assets become a liability!

Everyone is a content producer today - from the largest publishing house and entertainment studio, down to the smallest ecommerce store, corporate website or personal blog.

If content is the lifeblood of your website or application, images and videos form the heart that makes it tick and creates an emotional connection with the audience. But, using images and videos to make the content visually engaging and meet your conversion goals, you face a new challenge: managing your digital assets. Because the images and videos are created by different teams for different channels - such as website, social media, ecommerce store, blogs, partners and digital agencies to name a few - chaos can ensue.

Read more

Image Optimization in Python

By Prosper Otemuyiwa
Image Optimization in Python

Approximately 62 percent of today’s internet traffic is made up of images. Media-rich websites must ensure that all images are optimized to speed up the site. A faster site will make your visitors happy; and when they are happy you will likely see increased conversion rates.

Read more