Listen to this podcast:
Voiced by Amazon Polly

Image and video analysis have multiple use cases, be it face-based user verification, text detection, or identifying inappropriate content. Amazon has introduced such a service, which enables applications to detect and recognize faces, objects, scenes, etc. Like many other AWS services, Amazon Rekognition has gained popularity worldwide and is being adopted by many companies and institutions.

Amazon Rekognition is also one of the AWS services being tested on the AWS Certified Cloud Practitioner exam, albeit, at a very high level. Therefore, if you’re taking the exam, it’s good to have a basic understanding of the service.

What is Amazon Rekognition?

Amazon Rekognition is a service that enables you to easily integrate image and video analysis to your applications. It provides a powerful API that can detect and identify objects, people, activities, scenes, and text. It can also detect inappropriate content in the supplied images and videos.  A highly scalable tool, Amazon Rekognition can analyze billions of images and videos every day and does not require any machine learning expertise to use. The service is divided into two parts:

  1. Amazon Rekognition Image – Rekognition image is the API that detects and identifies faces, objects, and scenes. It also extracts texts, detects inappropriate content, and recognizes celebrities. The service enables you to compare faces for various use cases, including public safety, user verification, cataloging, and people counting.
  2.  Amazon Rekognition Video – Amazon Rekognition is the asynchronous API that analyzes videos stored in Amazon S3. It can detect activities, identify people and objects, and recognize celebrities. It also understands movement and detects inappropriate content in the video.

 

Amazon Rekognition Key Features and Use Cases

  1. Object, scene, and activity detection – Amazon Recognition can detect and identify objects and scenes in an image, as well as activities happening in a video such as “playing baseball.”
  2. Facial recognition –You can use Rekognition to identify faces in images, stored videos and streaming videos using your private repository of face images.
  3. Face-based user verification – With Amazon Rekognition, your applications can verify user identities by comparing their live image with a reference image.
  4. Searchable image and video libraries – Amazon Rekognition makes stored images and videos searchable, enabling you to discover objects and scenes within them.
  5. Sentiments and demographics analysis – With Rekognition, you can analyze the attributes of faces in images and videos. The tool can detect emotions such as happiness and sadness, and demographics like age range and gender.
  6. Text detection – Rekognition allows you to recognize and extract text and numbers from images, such as captions, street names, and license plates. You can use it in image sharing and social media applications, entertainment applications, as well as public safety applications.
  7. Unsafe content detection – Rekognition can identify inappropriate and unsafe content in images and videos. The returned metadata can help developers to control the content based on their business needs.
  8. Celebrity Recognition – Rekognition can quickly identify celebrities in supplied videos and images. It can recognize thousands of well-known people across different categories, such as sports, entertainment, politics, and business.

 

Benefits of Using Amazon Rekognition

  1. Simple integration – Amazon Rekognition makes it easy to add image recognition capabilities into your applications with a simple API.
  2. Deep learning technology – Amazon Rekognition employs deep learning technology to analyze images and videos. It’s continually trained on new data to improve and expand its ability to accurately identify objects, scenes, and activities.
  3. Scalable image analysis – With Rekognition, you can analyze millions of images
  4. Integration with other AWS services – Rekognition works seamlessly with other AWS services, such as AWS Lambda and Amazon S3.
  5. Low cost – The service does not have minimum fees or upfront commitments. You’re only charged for what you use.
  6. Fully managed – With Amazon Recognition, you get consistent response times irrespective of the volume of requests you make.
  7. Real-time analysis – Amazon Rekognition allows you to run real-time analysis on videos and images.

 

Amazon Rekognition Pricing

You only pay for the images analyzed, minutes of videos processed, and the amount of metadata stored. It also comes with a free tier to help you get started easily.