Intelligent Image Tagging
Automatic features and content detection
Atex content management solutions integrate with Amazon Rekognition in order to automatically identify objects, people, text, scenes, and activities, as well as detect any inappropriate content in images.
Amazon Rekognition is an image analysis service available in the Amazon AI suite which provides the following features:
Labels detection: identify thousands of objects (such as bike, telephone, building), and scenes (such as parking lot, beach, city)
Custom labels detection: identify objects and scenes which are unique to your business (ex. your logo, your business location, your products) thanks to a custom model built through of a console providing a visual interface to make labelling your images fast and simple. Custom face collections: identify faces which are listed in custom face collections created and maintained by the publisher
Content moderation: identify potentially unsafe or inappropriate content
Text detection: convert the detected text into machine-readable text
Celebrity recognition: identify well known people in your image libraries
Custom face collections: identify faces which are listed in custom face collections created and maintained by the publisher
Atex has integrated the image tagging service in its products specifically targeting the needs of its publishers customers, implementing features specifically useful for the journalism realm:
Children identification: detect images showing children faces and alert the editors so that the faces can be pixeled
Car number plate identification: detect images showing car number plates and alert the editors so that the numbers can be pixeled
Atex is also providing support to its customers in creating custom collections of faces and objects.
One of the main use cases of the image tagging service is linked to the image archives: re-indexing the old images and extracting texts, faces and labels will re-surface tons of interesting content.