# Amazon Rekognition Cloud service ยท AWS. Updated 2026-10-29. Page: https://blowstack.com/tools/cloud-services-hub/amazon-rekognition > Amazon Rekognition is a cloud-based software service that allows users to integrate image and video analysis using deep learning technology to identify objects, people, text, scenes, and activities, as well as detect potentially inappropriate content. Practice exams covering Amazon Rekognition: [AIB-C01 (beta) AWS Certified AI Business Strategist](https://blowstack.com/practice-exams/aws-certified-ai-business-strategist), [AIF-C01 AWS Certified AI Practitioner](https://blowstack.com/practice-exams/aws-certified-ai-practitioner), [CLF-C02 AWS Certified Cloud Practitioner](https://blowstack.com/practice-exams/aws-certified-cloud-practitioner), [MLA-C02 (beta) AWS Certified Machine Learning Engineer - Associate](https://blowstack.com/practice-exams/aws-certified-machine-learning-engineer-associate), [SAP-C02 AWS Certified Solutions Architect - Professional](https://blowstack.com/practice-exams/aws-certified-solutions-architect-professional). ## 6 key features of Amazon Rekognition Amazon Rekognition provides features for object and scene detection, facial analysis and recognition, text detection in images, unsafe content detection, and person tracking with activity recognition in images and videos. 1. **Object and Scene Detection**: Amazon Rekognition can identify thousands of objects (such as bike, telephone, building) and scenes (such as parking lot, beach, city) in images, allowing for rich image analysis and categorization. 2. **Facial Analysis**: This feature enables users to analyze faces in images and videos to detect attributes such as emotions (happy, sad, etc.), approximate age, gender, whether eyes are open, and the presence of glasses or facial hair. 3. **Facial Recognition**: Amazon Rekognition can compare faces in images and videos to a database of faces and find matches, useful in security applications or for indexing and managing video content. 4. **Text in Image**: With this feature, Amazon Rekognition can detect text in images, such as street names, captions, product names, and license plates, enabling automated text analysis in visual content. 5. **Unsafe Content Detection**: This feature helps in identifying potentially unsafe or inappropriate content across images and videos, aiding in content moderation workflows. 6. **Person Tracking and Activity Recognition**: Rekognition allows for the tracking of persons across frames in a video and recognizes activities such as 'running' or 'playing soccer', providing insights into human behavior in video content. ## Where Amazon Rekognition is used Amazon Rekognition facilitates automated content moderation, enhances security systems with facial recognition, improves searchability in media libraries, offers sentiment analysis in customer interactions, and enables personalized advertising through demographic insights. 1. **Automated Content Moderation**: Amazon Rekognition can automatically identify inappropriate or unsafe content within images and videos, enabling platforms and services to filter out harmful material before it reaches users. This use can greatly enhance user experience and comply with regulatory standards. 2. **Facial Recognition for Security Systems**: Integrating Amazon Rekognition into security systems allows for the identification and verification of individuals in real-time, enhancing security measures for premises. It can be used for access control in buildings, event monitoring, and maintaining logs of personnel movements. 3. **Intelligent Searchability in Media Libraries**: By analyzing and identifying objects, people, text, scenes, and activities in images and videos, Amazon Rekognition enables users to search and filter their media libraries using descriptive tags. This makes finding specific media content easier and more efficient. 4. **Sentiment Analysis in Customer Service**: Amazon Rekognition can analyze facial expressions in customer service interactions to gauge customer sentiments, providing valuable feedback on customer satisfaction and helping businesses tailor their services to improve customer experience. 5. **Personalized Advertising**: Using demographic information such as age or gender identified by Amazon Rekognition, businesses can tailor their advertising to target specific segments of their audience more effectively, thereby increasing engagement and conversion rates. ## How Amazon Rekognition is priced Amazon Rekognition pricing models include pay-as-you-go rates for image and video analysis based on volume, with separate rates for specific features and custom label detection, providing discounts at higher usage tiers. - **Amazon Rekognition Image**: Amazon Rekognition Image pricing is based on the number of images processed, with different rates for feature detection (such as object, scene, and activity detection, facial analysis, etc.) and facial recognition tasks. Pricing varies for the first millions of images processed monthly and decreases for subsequent images, offering volume discounts. - **Amazon Rekognition Video**: For video analysis, Amazon Rekognition Video charges are based on the minutes of video processed and the features used, such as pathing, activity detection, person tracking, etc. Stored video analysis is charged separately for each API run against the same section of video. - **Amazon Rekognition Custom Labels**: Custom Labels charges for training compute hours and for each hour the trained custom model is available to process images. Parallel compute resources increase the billed hours beyond elapsed time. - **Face Metadata Storage**: Face and user vectors stored for search incur monthly storage charges, prorated for partial months. - **Image Properties**: Calling DetectLabels with both IMAGE_PROPERTIES and GENERAL_LABEL incurs both the Image Properties and DetectLabels charges. - **Amazon Rekognition Face Liveness**: Face Liveness is billed per check, with monthly volume tiers for the first 500,000 checks, the next 2.5 million checks, and checks above 3 million. - **Amazon Rekognition Custom Moderation**: Custom Moderation charges for adapter training compute minutes and for each image analyzed with the adapter, with inference rates tiered by monthly image volume. ## Services Amazon Rekognition works with - **[Amazon S3](https://blowstack.com/tools/cloud-services-hub/amazon-s3)**: Amazon Rekognition can analyze images and videos stored in Amazon S3 buckets. By integrating with Amazon S3, you can trigger Rekognition operations on S3 objects using AWS Lambda or other event-driven triggers. - **[AWS Lambda](https://blowstack.com/tools/cloud-services-hub/aws-lambda)**: AWS Lambda can be triggered by Amazon Rekognition events to automate image and video processing workflows. For instance, when an image is uploaded to an S3 bucket, a Lambda function can automatically invoke Rekognition to analyze the image. ## What is Amazon Rekognition Amazon Rekognition is a sophisticated cloud-based service provided by Amazon Web Services (AWS) that integrates deep learning technology to enable applications to identify objects, people, text, scenes, and activities in images and videos, as well as detect potentially inappropriate content. Essentially, Rekognition makes it easier for developers to add image and video analysis to their applications without needing deep expertise in machine learning or computer vision technologies. At its core, Amazon Rekognition is designed to be highly accessible, allowing users to harness the power of advanced image and video analysis with simple API calls. This service is built on a scalable infrastructure, which means it can analyze billions of images and videos daily, supporting real-time analysis as well as batch processing. This scalability makes Rekognition an ideal solution for a wide range of applications, from social media content filtering to surveillance systems. One of the key features of Amazon Rekognition is its facial recognition capabilities. The service can detect, analyze, and compare faces for a variety of user verification, people counting, and public safety use cases. It can recognize and analyze attributes of faces in images and videos, such as emotions, age range, gender, and even facial movements, providing a comprehensive set of facial analysis data points. Moreover, Amazon Rekognition can identify objects and scenes within images and videos. This functionality enables developers to build applications that can categorize and organize vast amounts of visual data. It's particularly useful in retail and inventory management, where it can simplify product identification and automate cataloging. Another significant feature is its ability to detect unsafe or inappropriate content automatically. This capability is essential for social media platforms, online communities, and content publishers, helping them to moderate content in compliance with their policies and community standards efficiently. Custom Labels uses provisioned custom models. For periodic image processing, start provisioning at the scheduled time and stop provisioning after processing; leaving the model provisioned incurs charges even when no images are processed. Text detection and analysis is yet another crucial feature offered by Amazon Rekognition. It can detect and recognize text within images and videos - such as license plates, product names, and street signs, thereby enabling a myriad of use cases from traffic management systems to retail and advertising analytics. Amazon Rekognition is also designed with privacy and security in mind, providing users with robust data protection and access control mechanisms. AWS ensures that all data processed by Amazon Rekognition is encrypted in transit and at rest, incorporating user privacy and compliance into the service's architecture. In summary, Amazon Rekognition presents a versatile, powerful, and accessible cloud service that integrates advanced machine learning models for comprehensive image and video analysis. Its broad range of features supports a multitude of applications across various industries, making it an indispensable tool for developers and businesses looking to leverage sophisticated visual analysis capabilities without the need for deep technical expertise in AI or machine learning. ## Concepts related to Amazon Rekognition - [Machine learning](https://blowstack.com/tools/cloud-concepts-hub/machine-learning): Machine learning is a branch of artificial intelligence that uses data to train models to make predictions, recognize patterns, or generate outputs without explicitly programming every decision rule. - [Model Inference](https://blowstack.com/tools/cloud-concepts-hub/model-inference): Model inference is the process of applying a trained machine learning model to input data to produce predictions, scores, classifications, or generated content. - [Neural Networks](https://blowstack.com/tools/cloud-concepts-hub/neural-networks): Neural networks are machine learning models that learn patterns through interconnected layers of computational units with adjustable parameters. - [Unstructured Data](https://blowstack.com/tools/cloud-concepts-hub/unstructured-data): Unstructured data is information whose meaningful content does not fit a predefined tabular schema, such as free-form text, images, audio, and video.