Amazon Rekognition is a service that makes it easy to add image analysis to your applications. With Rekognition, you can detect objects, scenes, and faces in images. You can also search and compare faces, recognize celebrities, and identify inappropriate content.

To enable face searches, you can store collections of face metadata – vector representations of facial features. These vectors represent paths between prominent facial landmark points, such as left eye, right eye, nose, left corner of the mouth, and right corner of the mouth. Rekognition’s API enables you to quickly add sophisticated deep learning-based visual search and image classification to your applications. There are no upfront costs and you only pay for the images you analyze and the face metadata you store.

Deep learning-based image analysis lets applications gain a high-level understanding of the content of images. With image analysis, your applications can detect objects, scenes, and faces in image files. Organizations are using this new ability to accurately recognize the content of images quickly and at scale. This enables new capabilities and user experiences in applications, and lets you create entirely new categories of products. With image recognition, a door camera can visually recognize family members and trusted friends, unlock the door, turn on the lights, and adjust the temperature. Smart billboards can use image analysis to measure engagement based on the viewer’s facial attributes and emotions. With these same image analysis capabilities, photo apps can quickly organize millions of images based on the objects, scenes, and people pictured in them to enable fast and rich image search.

Amazon Rekognition is now generally available

Try Amazon Rekognition for Free
Or Sign in to the Console

Upon sign-up, new Amazon Rekognition customers can analyze 5,000 images per month and store up to 1,000 face metadata each month, for the first 12 months.

View AWS Free Tier Details »

Rekognition enables you to automatically identify thousands of objects, such as vehicles, pets, or furniture, and provides you with a confidence score for each object. Rekognition also detects scenes within the image, such as photos of a sunset or beach. To learn more about object and scene detection, see the Amazon Rekognition Developer Guide.

Rekognition enables you to detect explicit and suggestive content so that you can filter images based on your application requirements. Rekognition provides a hierarchical list of labels with confidence scores to enable fine-grained control over what images you want to allow.

With Rekognition, you can locate faces within images and analyze face attributes, such as whether the face is smiling, eyes are open, or showing emotions. When analyzing an image, Rekognition will return the position and a rectangular frame for each detected face along with landmark points such as left eye, right eye, nose, left corner of the mouth, and right corner of the mouth. This position information can be used to deliver additional functionality such as automatic face frames, highlights, or crops. You can also use this information to determine what portion of an image is filled by the face, to help you distinguish long shots from close-ups. To learn more about facial analysis, see the Amazon Rekognition Developer Guide.

Rekognition enables you to measure the likelihood that two facial images are of the same person, and provides a confidence score to help you evaluate the match. To learn more about Amazon Rekognition’s face comparison capabilities, see the Amazon Rekognition Developer Guide.

With Rekognition, you can find a face among millions of images. First, you create a face collection, where you can store faces, which are vector representations of facial features. You then specify a single photo, and Rekognition searches the face collection for visually similar faces. Rekognition will return a confidence score for each of the photos, so you can display likely matches in your application.

Rekognition detects and recognizes thousands of individuals who are famous, noteworthy, or prominent in their field. This allows you to index and search digital image libraries for celebrities based on your particular interest. The API provides the name and unique id of the celebrity, confidence of the match, and URLs pointing to related content for the celebrity, for example, the celebrity's IMDB link. For more details, see the documentation for the RecognizeCelebrities API.

Amazon Rekognition can be accessed using the Amazon Rekognition API, AWS Management Console, and the AWS command-line interface (CLI). The console, API, and CLI provide the ability to use the Rekognition APIs to detect labels, analyze faces, compare faces, and find a face. AWS Lambda has blueprints for Rekognition that make it easy to initiate image analysis based on events in your AWS data stores such as Amazon S3 and Amazon DynamoDB.

Amazon Rekognition is integrated with AWS Identity and Access Management (IAM). IAM policies can be used to control access to the Amazon Rekognition API as well as manage resource-level permissions for your account. 

Images analyzed using the Amazon Rekognition API are not stored and cannot be retrieved from Rekognition. If you want to search your face collection for similar faces, you can store face image metadata using the IndexFaces API function. You can then use the SearchFace function to find the best matching faces. Rekognition also provides an easy API to delete face metadata. To learn more about this API, please see the Amazon Rekognition Developer Guide.

For a summary of the Rekognition API, please see the API Reference in the Rekognition documentation.