Cloudinary Blog

Automatic image categorization and tagging with Imagga

Automatic Image Tagging and Categorization Using Imagga Api

If you have an application that allows users to upload their own photos, it can be very useful to be able to organize these photos according to their content. This will allow you to categorize the content for displaying to all your users and make your image library searchable. Furthermore, you can also learn more about your users according to the content they upload and find different trends of what people care about. Other added benefits can also include the ability to display matching content to your users according to their interests or even match them with other users that share similar interests.

Identifying images and their content is a process that would take huge amounts of time and resources if performed manually for many images. On the other hand, unlike text with words, images are data files with no meaning for simple software based filtering and require a deeper analysis of the actual meaning of the pixel colors in the image in order to automate the categorization and tagging process.

Imagga is a prominent company that develops and offers technologies, services, and online tools for visual image recognition, with technology that includes state-of-the-art machine learning approaches that allow it to be trained in the identification of various visual objects and concepts. In this post we would like to introduce you to a new add-on for Imagga's automatic image tagging capabilities, fully integrated into Cloudinary's image manipulation and management pipeline.

The Imagga Auto Tagging add-on

The Imagga add-on can automatically tell you what's in a photo by returning a list of detected tags and the confidence score of each tag.

The Imagga add-on is very simple to use: just set the categorization parameter of Cloudinary's image upload API to imagga_tagging while uploading an image and the response will include a list of suitable tags for the image.

For example, uploading the following picture of a koala to Cloudinary and requesting Imagga categorization:

Koala uploaded image for auto tagging

Ruby:
Cloudinary::Uploader.upload("koala.jpg",   
  :categorization => "imagga_tagging")
PHP:
\Cloudinary\Uploader::upload("koala.jpg",   
  array("categorization" => "imagga_tagging"));
Python:
cloudinary.uploader.upload("koala.jpg",  
  categorization = "imagga_tagging")
Node.js:
cloudinary.uploader.upload("koala.jpg",   
  function(result) { console.log(result); },   
  { categorization: "imagga_tagging" });
Java:
cloudinary.uploader().upload("koala.jpg", ObjectUtils.asMap(  
  "categorization", "imagga_tagging"));

The response will include the automatic categorization identified by the Imagga add-on. As can be seen in the response snippet below, various categories were automatically detected in the uploaded photo. The confidence score is a numerical value that represents the confidence level of the detected category, where 1.0 means 100% confidence. So Imagga is 100% sure that the picture contains a koala and only 8.5% sure that the picture contains a baboon.


"info"=>{
  "categorization"=>{
    "imagga_tagging"=>{
      "status"=>"complete", 
      "data"=>[
        {"tag"=>"koala", "confidence"=>1.0}, 
        {"tag"=>"mammal", "confidence"=>0.3151}, 
        {"tag"=>"monkey", "confidence"=>0.0882}
        {"tag"=>"baboon", "confidence"=>0.0853}

You can also get a list of tags from an already uploaded image by using the update method in Cloudinary's Admin API together with the image's public ID. For example, requesting Imagga categorization for the already uploaded image with a public ID of landscape:

Landscape photo for auto image tagging

Ruby:
Cloudinary::Api.update("landscape",   
  :categorization => "imagga_tagging")
PHP:
\Cloudinary\Api::update("landscape",   
  array("categorization" => "imagga_tagging"));
Python:
cloudinary.api.update("landscape",  
  categorization = "imagga_tagging")
Node.js:
cloudinary.api.update("landscape",   
  function(result) { console.log(result); },   
  { categorization: "imagga_tagging"});
Java:
cloudinary.api().update("landscape", ObjectUtils.asMap(  
  "categorization", "imagga_tagging"));

As with the upload API, the response includes the automatic categorization identified by Imagga shown in the response snippet below, where, for example, "landscape" is identified with 54% confidence, "grass" is identified with 44% confidence, along with a variety of other categories that may be relevant depending on your categorization scheme.


"info"=>{
  "categorization"=>{
    "imagga_tagging"=>{
      "status"=>"complete", 
      "data"=>[
        {"tag"=>"landscape", "confidence"=>0.5475}, 
        {"tag"=>"grass", "confidence"=>0.4414}, 
        {"tag"=>"field", "confidence"=>0.4121}, 
        {"tag"=>"sky", "confidence"=>0.394}, 
        {"tag"=>"land", "confidence"=>0.3514}, 
        {"tag"=>"rural", "confidence"=>0.3498}, 
        {"tag"=>"grassland", "confidence"=>0.3464}, 
        {"tag"=>"meadow", "confidence"=>0.3403}

Automatic tagging

If you want to organize, browse and manage your images based on the categories identified by Imagga, you can also automatically assign Cloudinary's resource tags to uploaded images.

Add the auto_tagging API parameter and set it to a minimum confidence level threshold, where all detected categories with a confidence level above this value will be automatically assigned that category as a resource tag.

For example, to automatically add tags to the landscape image with all detected categories that have a score higher than 0.4.

Ruby:
Cloudinary::Uploader.upload("landscape.jpg", 
  :categorization => "imagga_tagging", :auto_tagging => 0.4)
PHP:
\Cloudinary\Uploader::upload("landscape.jpg", 
  array("categorization" => "imagga_tagging", "auto_tagging" => 0.4));
Python:
cloudinary.uploader.upload("landscape.jpg",
  categorization = "imagga_tagging", auto_tagging = 0.4)
Node.js:
cloudinary.uploader.upload("landscape.jpg", 
  function(result) { console.log(result); }, 
  { categorization: "imagga_tagging", auto_tagging: 0.4 });
Java:
cloudinary.uploader().upload("landscape.jpg", ObjectUtils.asMap(
  "categorization", "imagga_tagging", "auto_tagging", "0.4"));

The response of the upload API call above returns the detected categories as well as the assigned tags. In this case, only the 'landscape', 'grass' and 'field' categories have a high enough score to be used as tags.

{ 
  ...    
  "tags" => [ "landscape", "grass", "field" ]   
  ...  
}

You can also use the update method to apply Imagga auto tagging to already uploaded images, based on their public IDs, and then automatically tag them according to the detected categories. See the Imagga add-on documentation for more information.

Categorization of images made easy

Categorizing photos can be a very useful and powerful tool that you can utilize to understand and organize the images that are uploaded by your users. Using the Imagga add-on as part of Cloudinary's service is simple and streamlined: you just need to add a parameter as part of the Cloudinary image upload and manipulation process.

Imagga add-on plans

The Imagga Auto Tagging add-on is available now and all Cloudinary plans can try it out with the add-on’s free tier. If you don't have a Cloudinary account yet, you can easily sign up for a free account.

Recent Blog Posts

Integrating Cloudinary with Forestry’s Media Library

At Forestry, we believe that there is a bright future for static HTML sites built with tools like Jekyll and Hugo. These tools can create sites that run well, and are easy to host and maintain, because they don’t require any server-side code.

Read more
Video Optimization With the HTML5 <video> Player

Lack of experience and compression knowhow can cause significant user-experience problems. For instance, on a major retail site, I recently ran into a 48 MB video-hero banner. Pulling out the video and encoding it as an H.264 MP4 reduces the size to 1.9 MB. So, despite the desire for more video content, developers have not yet caught up to best practices. How do we get the best of both worlds without creating a disaster like the one above?

Read more
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!

Read more
Improve Customer Data Protection with GDPR Implementation

TL;DR

Yay! We've done it! Gold-Star for us! We've talked with all the people, made all the changes, paid all the lawyers and checked all the boxes. GDPR? ✅Done!

Not so fast. Of course, conforming to the GDPR regulations introduced in Europe is just the beginning. This is a process and a state of mind that must become part of our long-term cultural ethos.

Read more
Magento Image and Video Optimization

As the number of channels and devices continues to grow, it is becoming much more challenging to deliver an optimal visual experience. On an eCommerce site, engagement and conversions are critical. Factors such as page load time strongly influence search engine rankings, shopping experiences, conversion rates and, ultimately, your revenue. An optimized visual experience positively affects conversion rates. But it also can introduce resource bottlenecks, as every image and video needs to be delivered in the most efficient format, quality and resolution, based on the viewing device.

Read more