What is Amazon Rekognition? - Amazon Rekognition

What is Amazon Rekognition?

Amazon Rekognition makes it easy to add image and video analysis to your applications. You just have to provide an image or video to the Amazon Rekognition API, and the service can:

  • Identify labels (objects, concepts, people, scenes, and activities) and text

  • Detect inappropriate content

  • Provide highly accurate facial analysis, face comparison, and face search capabilities

With Amazon Rekognition's face recognition APIs, you can detect, analyze, and compare faces for a wide variety of use cases, including user verification, cataloging, people counting, and public safety.

Amazon Rekognition is based on the same proven, highly scalable, deep learning technology developed by Amazon’s computer vision scientists to analyze billions of images and videos daily. It requires no machine learning expertise to use. Amazon Rekognition includes a simple, easy-to-use API that can quickly analyze any image or video file that’s stored in Amazon S3. It's always learning from new data, and we’re continually adding new labels and facial comparison features to the service.

For more information, see the Amazon Rekognition FAQs.

Common use cases for using Amazon Rekognition include the following:

  • Searchable image and video libraries – Amazon Rekognition makes images and stored videos searchable so you can discover labels (objects, concepts, and scenes) that appear within them.


  • Face Liveness Detection– Amazon Rekognition Face Liveness is a fully managed machine learning (ML) feature designed to help developers deter fraud in face-based identity verification. The feature helps you verify that a user is physically present in front of the camera and isn’t a bad actor spoofing the user's face. Using Rekognition Face Liveness can help you detect spoof attacks presented to a camera, such as printed photos, digital photos/videos, or 3D masks. It also helps detect spoof attacks that bypass a camera, such as pre-recorded or deepfake videos injected directly into the video capture subsystem.


  • Face-based user verification – Amazon Rekognition enables your applications to confirm user identities by comparing their live image with a reference image.


  • Facial detection and analysis – Amazon Rekognition can detect and analyze different facial components and attributes, such as: emotional expressions (like happy, sad, or surprised), demographic information (like gender or age), face occlusion (when a face's eyes, nose, and/or mouth are blocked by dark sunglasses, masks, hands, etc), and eye gaze direction (as defined by pitch and yaw). Amazon Rekognition can analyze images, and send the emotion and demographic attributes to Amazon Redshift for periodic reporting on trends such as in store locations and similar scenarios. Note that a prediction of an emotional expression is based on the physical appearance of a person's face only. It is not indicative of a person’s internal emotional state, and Rekognition should not be used to make such a determination.


  • Facial Search – With Amazon Rekognition, you can search images, stored videos, and streaming videos for faces that match those stored in a container known as a face collection. A face collection is an index of faces that you own and manage. Searching for people based on their faces requires two major steps in Amazon Rekognition:

    1. Index the faces.

    2. Search the faces.


  • Detection of Personal Protective Equipment

    Amazon Rekognition detects Personal Protective Equipment (PPE) such as face covers, head covers, and hand covers on persons in images. You can use PPE detection where safety is the highest priority. For example, industries such as construction, manufacturing, healthcare, food processing, logistics, and retail. With PPE detection, you can automatically detect if a person is wearing a specific type of PPE. You can use the detection results to send a notification or to identify places where safety warnings or training practices can be improved.


  • Unsafe content detection – Amazon Rekognition can detect inappropriate, unwanted, or offensive content. The Content Moderation API also returns a hierarchical list of detected labels (objects and concepts), along with confidence scores. These objects/labels indicate specific categories of unsafe content, which enables you to filter specific concepts and manage large volumes of user-generated content (UGC). The API can also identify animated or illustrated content type, which is returned as part of the API response. You can customize the output of the Content Moderation API with adapters, which allow you to fine tune the model with your data and can enhance model performance on images similar to the data that you use to fine tune the model.


  • Celebrity recognition – Amazon Rekognition can recognize celebrities within supplied images and in videos. Amazon Rekognition can recognize thousands of celebrities across a number of categories, such as politics, sports, business, entertainment, and media.


  • Text detection – Amazon Rekognition Text in Image enables you to recognize and extract textual content from images. Text in Image supports most fonts, including highly stylized ones. It detects text and numbers in different orientations, such as those commonly found in banners and posters. In image sharing and social media applications, you can use it to enable visual search based on an index of images that contain the same keywords. In media and entertainment applications, you can catalog videos based on relevant text on screen, such as ads, news, sport scores, and captions. Finally, in public safety applications, you can identify vehicles based on license plate numbers from images taken by street cameras.


  • Custom labels– With Amazon Rekognition Custom Labels, you can identify the labels (objects and concepts) and scenes in images that are specific to your business needs. For example, you can find your logo in social media posts, identify your products on store shelves, classify machine parts in an assembly line, distinguish healthy and infected plants, or detect animated characters in videos. For more information, see What is Amazon Rekognition Custom Labels? in the Amazon Rekognition Custom Labels Developer Guide.


Some of the benefits of using Amazon Rekognition include:

  • Integrating powerful image and video analysis into your apps – You don’t need computer vision or deep learning expertise to take advantage of the reliable image and video analysis in Amazon Rekognition. With the API, you can build image and video analysis into any web, mobile, or connected device application.


  • Deep learning-based image and video analysis – Amazon Rekognition uses deep-learning technology to accurately analyze images, find and compare faces in images, and detect labels (objects, scenes, and concepts) within your images and videos. You can analyze images for the presence of many different labels and then filter the results to include and/or exclude sets of labels or label categories.


  • Scalable image analysis – Amazon Rekognition enables you to analyze millions of images so you can curate and organize massive amounts of visual data.


  • Analyze and filter images based on image properties – Amazon Rekognition lets you analyze image properties like quality or colors. You can determine the sharpness, brightness, and contrast of images. You can also detect dominant colors in the entire image, foreground, background, and objects/labels with bounding boxes.


  • Integration with other AWS services – Amazon Rekognition is designed to work seamlessly with other AWS services like Amazon S3 and AWS Lambda. You can call the Amazon Rekognition API directly from Lambda in response to Amazon S3 events. Because Amazon S3 and Lambda scale automatically in response to your application’s demand, you can build scalable, affordable, and reliable image analysis applications. For example, each time a person arrives at your residence, your door camera can upload a photo of the visitor to Amazon S3. This triggers a Lambda function that uses Amazon Rekognition API operations to identify your guest. You can run analysis directly on images that are stored in Amazon S3 without having to load or move the data. Support for AWS Identity and Access Management (IAM) makes it easy to securely control access to Amazon Rekognition API operations. Using IAM, you can create and manage AWS users and groups to grant the appropriate access to your developers and end users.


  • Low cost – With Amazon Rekognition, you pay for the images and videos that you analyze, and the face metadata that you store. There are no minimum fees or upfront commitments. You can get started for free, and save more as you grow with the Amazon Rekognition tiered pricing model.

  • Simple customization - Some Amazon Rekognition Image analysis APIs let you enhance the accuracy of object classification and detection by creating adapters trained on your own data. You create an adapter tuned to your specific use case by providing and annotating sample images. You can then specify the adapter when calling any operation that supports it.

Amazon Rekognition and HIPAA eligibility

This is a HIPAA Eligible Service. For more information about AWS, U.S. Health Insurance Portability and Accountability Act of 1996 (HIPAA), and using AWS services to process, store, and transmit protected health information (PHI), see HIPAA Overview.

Are you a first-time Amazon Rekognition user?

If you're a first-time user of Amazon Rekognition, we recommend that you read the following sections in order:

  1. How Amazon Rekognition works – This section introduces various Amazon Rekognition components that you work with to create an end-to-end experience.

  2. Getting started with Amazon Rekognition – In this section, you set up your account, install the SDK that reflects the language of your choice, and test the Amazon Rekognition API. For a list of the programming languages supported by Amazon Rekognition, see Using Rekognition with an AWS SDK.

  3. Working with images – This section provides information about using Amazon Rekognition with images stored in Amazon S3 buckets and images loaded from a local file system.

  4. Working with stored video analysis – This section provides information about using Amazon Rekognition with videos stored in an Amazon S3 bucket.

  5. Working with streaming video events – This section provides information about using Amazon Rekognition with streaming videos.