Rekognition is part of the AWS suite of artificial intelligence capabilities which are pre-trained, providing years and years of extensive research, deep-learning algorithms and machine learning models into simple API calls ready for developers to embrace and use.
Like its other AI services, Rekognition frees developers to focus on making apps that will see, hear, speak, understand and interact with the world around them, without having to invest in the mathematics or research or infrastructure that would otherwise have been needed; truly it is AI-as-a-service, bringing the benefits of Amazon's research to others.
“Since the launch of the AWS Sydney Region just over five years ago, AWS’s Australian and New Zealand customers have used AWS to remediate the costs and limitations of their legacy environments, to accelerate agility and innovation, and to support their digital transformation agendas,” said Paul Migliorini, Amazon Web Services managing director, Australia and New Zealand.
A number of Australian AWS customers already use Amazon Rekognition, including Airtasker, Social Soup, and Domain. Sharyn Smith, founder and chief executive of Social Soup, said using Amazon Rekognition has helped Social Soup provide its clients with real time customer behaviour analysis, and match marketing campaigns to customers more efficiently. “The availability of Amazon Rekognition in the AWS Sydney Region will enhance Social Soup’s ability to deliver more sophisticated campaign marketing solutions to our customers faster, and at scale.”
Rekognition is a result of more than 20 years of investment in artificial intelligence at Amazon. Using deep learning technologies, Amazon Rekognition can track people, detect activities, and recognize objects, faces, celebrities, and inappropriate content in millions of videos stored in Amazon S3. It also provides real-time facial recognition across millions of faces for live stream videos.
In addition, the service can locate faces within images and detect attributes, such as whether or not the face is smiling or the eyes are open. Using Rekognition’s easy to use API, developers can build an application that measures the likelihood that faces in two images are of the same person, thereby being able to verify a user against a reference photo in near real-time. Similarly, developers can create collections of millions of faces (detected in images) and can search for a face similar to their reference image in the collection.
Amazon Rekognition ic claimed to help remove the complexity and overhead required to develop and manage expensive image processing pipelines by making comprehensive image classification, detection, and management capabilities available in a simple and cost-effective AWS service.