Amazon Rekognition allows you to detect objects and scene details from images. It provides a stateless and secure API that simply returns a list of related labels, with a certain confidence level.

In this hands-on lab, you will build a serverless system that runs object detection when images are uploaded to an Amazon S3 bucket. You will use AWS Lambda for the processing logic and you will use Amazon DynamoDB to store the results of the label detection.

Learning Objectives

Upon completion of this beginner-level lab, you will be able to:

• Create an Amazon S3 bucket
• Create an AWS Lambda function
• Configure an AWS Lambda function to trigger on an upload to Amazon S3
• Implement image label detection using Amazon Rekognition and Python

Intended Audience

• Cloud Engineers
• Data Engineers

Prerequisites

Knowledge of the following will be beneficial but is not required:

• Amazon S3
• AWS Lambda
• Amazon Rekognition
• Python

The following courses can be used to fulfill the prerequisites:

• Introduction to Amazon Rekognition
• Storage Fundamentals for AWS
• Compute Fundamentals For AWS
• Python for Beginners

Updates

March 11th, 2021 - Updated AWS Lambda lab steps to reflect latest user interface updates

January 22nd, 2021 - Updated AWS Lambda lab steps to reflect latest user interface updates

December 8th, 2020 - Updated all instructions and screenshots to address issues with the UI being outdated

February 21st, 2020 - Updated instructions to clarify the need to use the provided code and the detect labels API for the lab to function correctly

January 10th, 2019 - Added a validation Lab Step to check the work you perform in the Lab