Amazon Rekognition is a machine learning (ML) based service that can analyze images and videos to detect objects, people, faces, text, scenes, activities, and inappropriate content. Label Detection makes it easy for customers to detect thousands of objects, scenes, actions, or concepts found in an image or video based on its contents. For example, a photo taken during a tropical beach holiday may contain labels such as ‘Palm Tree’ (object), ‘Beach’ (scene), ‘Running’ (action), and ‘Outdoors’ (concept). In addition, Amazon Rekognition provides bounding boxes for common objects such as cars, furniture, apparel, or pets. Starting today, customers can view the complete list of labels and object bounding boxes supported by Amazon Rekognition, to quickly identify those that are relevant to their applications and use cases.
Label detection provides rich image and video metadata that makes it easy to automate or enhance a variety of use cases such as image and video search for user generated content, contextual advertising against produced content, and performance analysis of marketing material. For example, a social media platform can offer a feature that allows users to search for any photo and video that contains a ‘Beach’ or a ’Golden Retriever’ dog. On the other hand, a media publisher looking to monetize their video content may use this type of metadata to place a contextually relevant advertisement for a family beach holiday. A marketing technology company may use labels metadata to analyze which visual elements in the creative led to higher campaign conversion and user engagement.
Customers can download the list of supported labels and object bounding boxes from our documentation page or from the ‘Label detection’ tab of the Amazon Rekognition Console. In addition, on the Rekognition console, customers can use a search bar to easily check whether their label is already supported or not. Using the same interface, customers can request new labels that they would like Amazon Rekognition to support, or provide any other product feedback.
News Source : www.aws.amazon.com