Imagga Auto Tagging
Overview
Cloudinary is a cloud-based service that provides an end-to-end image management solution including uploads, storage, manipulations, optimizations and delivery. Cloudinary offers a very rich set of image manipulation and analysis capabilities and allows you to extract the semantic data from uploaded images: photo metadata (Exif & IPTC) including location and camera details, coordinates of automatically detected faces, color histogram and predominant colors. In addition, Cloudinary allows you to assign multiple tags to images for listing and managing your media library.
Imagga develops and offers technologies, services, and online tools for visual image recognition. Cloudinary provides an add-on for Imagga's automatic image tagging capabilities, fully integrated into Cloudinary's image management and manipulation pipeline. Imagga analyses image data and automatically identifies scenes and suggests tags, a process that would take huge amounts of time and resources if performed manually. Imagga's technology includes state-of-the-art machine learning approaches that allow it to be trained in the recognition of various visual objects and concepts. Combined with big manually created data sets containing the visual characteristics of images and their associated tags, results in outstanding performance in terms of the time needed to process large photo volumes with a very high precision rate.
With the Imagga auto tagging add-on, you can extend Cloudinary's powerful semantic data extraction and image tagging features. When using the Imagga auto tagging add-on, your images are automatically tagged according to the categories detected in each image.
Image recognition and categorization
Take a look at the following photo, depicting some turtles:
cl_image_tag("turtles.jpg")cl_image_tag("turtles.jpg")CloudinaryImage("turtles.jpg").image()cloudinary.image("turtles.jpg")cloudinary.url().imageTag("turtles.jpg")$.cloudinary.image("turtles.jpg")
cloudinary.Api.UrlImgUp.BuildImageTag("turtles.jpg")
By setting the categorization parameter to imagga_tagging when calling Cloudinary's upload API, Imagga is used to automatically classify the scenes of the uploaded photo.
Cloudinary::Uploader.upload("turtles.jpg", :categorization => "imagga_tagging")
\Cloudinary\Uploader::upload("turtles.jpg", array("categorization" => "imagga_tagging"));
cloudinary.uploader.upload("turtles.jpg", categorization = "imagga_tagging")
cloudinary.uploader.upload("turtles.jpg", function(result) { console.log(result); }, { categorization: "imagga_tagging" });
cloudinary.uploader().upload("turtles.jpg", ObjectUtils.asMap( "categorization", "imagga_tagging"));
The upload API response includes the automatic categorization identified by the Imagga auto tagging 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.
{
...
"info": {
"categorization": {
"imagga_tagging": {
"status": "complete",
"data": [
{ "tag": "sea turtle", "confidence": 1.0 },
{ "tag": "loggerhead", "confidence": 1.0 },
{ "tag": "turtle", "confidence": 0.8903 },
{ "tag": "crab", "confidence": 0.3089 },
{ "tag": "king crab", "confidence": 0.2722 },
{ "tag": "crustacean", "confidence": 0.1587 },
{ "tag": "dungeness crab", "confidence": 0.1102 },
{ "tag": "sea", "confidence": 0.1049 },
{ "tag": "water", "confidence": 0.0986 },
{ "tag": "ocean", "confidence": 0.0849 },
{ "tag": "arthropod", "confidence": 0.0764 },
{ "tag": "fish", "confidence": 0.0755 }]}}}Adding resource tags to images
Automatically categorizing your images is a useful way to organize your Cloudinary media library, and by also providing the auto_tagging parameter to the upload call, images are automatically assigned resource tags based on the detected scene categories. The value of the auto_tagging parameter is the minimum confidence score of a detected category that should be automatically used as an assigned resource tag. Assigning these resource tags allows you to list and search images in your media library using Cloudinary's API and Web interface.
The following code sample automatically tags an uploaded image with all detected categories that have a score higher than 0.4.
Cloudinary::Uploader.upload("turtles.jpg", :categorization => "imagga_tagging", :auto_tagging => 0.4)
\Cloudinary\Uploader::upload("turtles.jpg", array("categorization" => "imagga_tagging", "auto_tagging" => 0.4));
cloudinary.uploader.upload("turtles.jpg", categorization = "imagga_tagging", auto_tagging = 0.4)
cloudinary.uploader.upload("turtles.jpg", function(result) { console.log(result); }, { categorization: "imagga_tagging", auto_tagging: 0.4 });
cloudinary.uploader().upload("turtles.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 'sea turtle', 'loggerhead' and 'turtle' categories have a high enough score to be used as tags.
{
...
"tags" => [ "sea turtle", "loggerhead", "turtle" ]
...Multi-language support
The automatic image categorization and tagging features also support multiple languages. You can get results in other languages by adding the 2-letter Language Code to the categorization parameter value of imagga_tagging, separating each additional language with a colon. For example, to get results in Finnish (fi) and Danish (da), set the value to imagga_tagging:fi:da. The full list of supported languages and their language codes can be found here.
Update existing images
The examples given above have shown how to automatically detect scene categories and auto tag images during their upload process. You can also use the update method in Cloudinary's Admin API to apply Imagga auto tagging to already uploaded images, based on their public IDs, and then automatically tag them according to the detected categories.
For example, the following image was uploaded to Cloudinary with the 'sample' public ID.
cl_image_tag("sample.jpg")cl_image_tag("sample.jpg")CloudinaryImage("sample.jpg").image()cloudinary.image("sample.jpg")cloudinary.url().imageTag("sample.jpg")$.cloudinary.image("sample.jpg")
cloudinary.Api.UrlImgUp.BuildImageTag("sample.jpg")
The following code sample uses Cloudinary's update method to apply Imagga's automatic image tagging and categorization to the sample uploaded image, and then automatically assign resource tags based on the categories detected with over a 50% confidence level.
Cloudinary::Api.update("sample", :categorization => "imagga_tagging", :auto_tagging => 0.5)
\Cloudinary\Api::update("sample", array("categorization" => "imagga_tagging", "auto_tagging" => 0.5));
cloudinary.api.update("sample", categorization = "imagga_tagging", auto_tagging = 0.5)
cloudinary.api.update("sample", function(result) { console.log(result); }, { categorization: "imagga_tagging", auto_tagging: 0.5 });
cloudinary.api().update("sample", ObjectUtils.asMap( "categorization", "imagga_tagging", "auto_tagging", 0.5));
The response of the update API call includes the detected categories, and automatically assigned tags. As you can see in the response snippet below, the 'pink' and 'flower' scene categories were detected with a confidence score of over 50%, which led to them being auto assigned as tags.
{
...
"tags": [ "pink", "flower" ]
"info": {
"categorization": {
"imagga_tagging": {
"status": "complete",
"data": [
{ "tag": "pink", "confidence": 0.822 },
{ "tag": "flower", "confidence": 0.6306 },
{ "tag": "flowers", "confidence": 0.3778 },
{ "tag": "plant", "confidence": 0.3667
...
}You can use the Admin API's show resource details method to list the scene categories that were previously extracted either using the 'upload' or 'update' API.