Explain the features of Amazon Rekognition

In this recipe, we will learn about Amazon Rekognition We will also learn about the features of Amazon Rekognition.

Recipe Objective - Explain the features of Amazon Rekognition?

The Amazon Rekognition is widely used and is defined as the computer vision service which was introduced by Amazon in the 2016 year. Amazon Rekognition automates user's image and video analysis with machine learning capabilities. The computer vision service which is provided by Amazon Rekognition is divided into two categories: which can be divided into two categories i.e.firstly, the algorithms that are pre-trained on data collected by the Amazon or its partners and the algorithms that a user can train on the custom dataset. Amazon Rekognition enables the quick addition of the pre-trained or the customizable computer vision APIs to user's applications without the need of building machine learning (ML) models and the infrastructure from scratch. Amazon Rekognition also scales up and down based on user's business needs with the fully managed Artificial Intelligence capabilities and users can pay only for the images and videos they analyze. Amazon Rekognition enables users to analyze millions of images and videos within minutes and further augment human visual review tasks with artificial intelligence (AI) capabilities. Amazon Rekogniton provides amazon rekognition Activities Package brings the power of the Amazon Rekognition image service to the UiPath Studio so, using the Amazon Rekognition Image APIs, the activities package provides users with the image analysis capabilities like Detect, identify, and compare faces & Identify and return distinct objects (Eg. label detection) & Detect unsafe content & Identify and return text & Create collections for storing faces.

Access Snowflake Real-Time Project to Implement SCD's

Benefits of Amazon Rekognition

  • The Amazon Rekognition helps in detecting text in images and videos. Amazon Rekognition can further convert the detected text into the machine-readable text and users can use the machine-readable text detection in images to implement solutions like Visual search that is retrieving & displaying images that contain the same text. Users can also implement Content insights that are providing insights into themes that occur in the text that's recognized in extracted video frames and the user's application can search recognized text for the relevant content, such as the news, sports scores, athlete numbers, and captions. Further, users can implement Navigation which is developing a speech-enabled mobile app for the visually impaired people which recognizes names of the restaurants, shops, or street signs. Following Public safety and transportation support that is detecting car license plate numbers from the traffic camera images and further Filtering that is filtering the personally identifiable information (PII) from various images. Amazon Rekognition automates the Personal Protective Equipment (PPE) detection to improve workplace safety practices and thus provide workplace safety. Amazon Rekognition augments manual checks with the automated PPE detection and Analyze images from cameras across all user's on-premises sites to detect if employees and customers are wearing PPE were required and thus automating PPE detection at scale. Further, It alerts or notifies the employees and customers about missing PPE in time to prevent lapses and improve everyone’s safety. and helps in maintaining the PPE detection records to comply with the occupational safety regulations and further reduce the risk of penalties or fines so, it helps in reducing the financial and human risk. The Amazon Rekognition provides users with the option to pay for the images and videos that they analyze, and the face metadata that they store and there are no minimum fees or upfront commitments. So, Users can get started for free, and save more as they grow with the Amazon Rekognition tiered pricing model and thus providing Low-cost service.

System Requirements

  • Any Operating System(Mac, Windows, Linux)

This recipe explains Amazon Rekognition and Features of Amazon Rekognition.

Features of Amazon Rekognition

    • It enables Detection and Analyzes Faces

Amazon Rekognition can detect the faces in images and videos. Users can get the information about where faces are detected in an image or video, facial landmarks such as the position of the eyes, and detected the emotions (for example, appearing happy or sad). Users can also compare the face in an image with faces detected in the another image. When Users provide an image which contains the face, Amazon Rekognition detects the face in the image, analyzes facial attributes of the face, and then returns the per cent confidence score for the face and the facial attributes which are detected in the image.

    • It helps in Moderating Content

Amazon Rekognition helps in detecting the content which is inappropriate, unwanted, or offensive. Users can use the Rekognition moderation APIs in social media, broadcast media, advertising, and the e-commerce situations to create a safer user experience, provide brand safety assurances to advertisers and users, and comply with the local and global regulations. Amazon Rekognition for image and video moderation enables human moderators to review a much smaller set of content which is typically 1-5% of the total volume which is already flagged by machine learning. This enables them to focus on more valuable activities and still achieve the comprehensive moderation coverage at a fraction of their existing cost. Amazon Augmented AI can be used to set up human workforces and perform human review tasks which come integrated with Amazon Rekognition.

    • It provides Face detection and analysis

Amazon Rekognition can store information about detected faces in the server-side containers known as the collections. Users can use the facial information that's stored in the collection to search for known faces in images, stored videos, and the streaming videos. Amazon Rekognition supports the IndexFaces operation so, Users can use this operation to detect the faces in an image and persist information about the facial features which are detected into the collection.

    • It detects Labels

Amazon Rekognition Image and Amazon Rekognition Video can return bounding boxes for the common object labels such as cars, furniture, apparel or the pets. The Bounding box information isn't returned for less common object labels. Users can use the bounding boxes to find the exact locations of objects in an image, count instances of the detected objects, or to measure an object's size using the bounding box dimensions. Amazon Rekognition Image and Amazon Rekognition Video use the hierarchical taxonomy of ancestor labels to further categorize the labels. For eg., a person walking across the road might be detected as a Pedestrian.

    • It provides Detection of video segments in the stored video

Amazon Rekognition Video provides an API that identifies the useful segments of video, such as black frames and end credits. Amazon Rekognition Video can be used to automate the operational media analysis tasks using the fully managed, purpose-built video segment detection APIs powered by the machine learning (ML). By using the Amazon Rekognition Video segment APIs, Users can easily analyze large volumes of videos and detect the markers such as the black frames or some shot changes.

What Users are saying..

profile image

Ray han

Tech Leader | Stanford / Yale University
linkedin profile url

I think that they are fantastic. I attended Yale and Stanford and have worked at Honeywell,Oracle, and Arthur Andersen(Accenture) in the US. I have taken Big Data and Hadoop,NoSQL, Spark, Hadoop... Read More

Relevant Projects

Create A Data Pipeline based on Messaging Using PySpark Hive
In this PySpark project, you will simulate a complex real-world data pipeline based on messaging. This project is deployed using the following tech stack - NiFi, PySpark, Hive, HDFS, Kafka, Airflow, Tableau and AWS QuickSight.

Airline Dataset Analysis using PySpark GraphFrames in Python
In this PySpark project, you will perform airline dataset analysis using graphframes in Python to find structural motifs, the shortest route between cities, and rank airports with PageRank.

Real-time Auto Tracking with Spark-Redis
Spark Project - Discuss real-time monitoring of taxis in a city. The real-time data streaming will be simulated using Flume. The ingestion will be done using Spark Streaming.

SQL Project for Data Analysis using Oracle Database-Part 2
In this SQL Project for Data Analysis, you will learn to efficiently analyse data using JOINS and various other operations accessible through SQL in Oracle Database.

PySpark ETL Project for Real-Time Data Processing
In this PySpark ETL Project, you will learn to build a data pipeline and perform ETL operations for Real-Time Data Processing

Azure Data Factory and Databricks End-to-End Project
Azure Data Factory and Databricks End-to-End Project to implement analytics on trip transaction data using Azure Services such as Data Factory, ADLS Gen2, and Databricks, with a focus on data transformation and pipeline resiliency.

GCP Project to Explore Cloud Functions using Python Part 1
In this project we will explore the Cloud Services of GCP such as Cloud Storage, Cloud Engine and PubSub

Streaming Data Pipeline using Spark, HBase and Phoenix
Build a Real-Time Streaming Data Pipeline for an application that monitors oil wells using Apache Spark, HBase and Apache Phoenix .

Build a Data Pipeline in AWS using NiFi, Spark, and ELK Stack
In this AWS Project, you will learn how to build a data pipeline Apache NiFi, Apache Spark, AWS S3, Amazon EMR cluster, Amazon OpenSearch, Logstash and Kibana.

Migration of MySQL Databases to Cloud AWS using AWS DMS
IoT-based Data Migration Project using AWS DMS and Aurora Postgres aims to migrate real-time IoT-based data from an MySQL database to the AWS cloud.