Tuesday 19 March 2019

AWS Rekognition for beginners

aws rekognition for beginners

Question: What is Amazon Rekognition?
Amazon Rekognition makes it easy to add image/video analysis to your applications.


Question: What different data we can get from Rekognition?
--Detect Objects and scenes that appear in photo/video.
--Face-based user verification.
--Detect Sentiment such as happy, sad, or surprise
--Unsafe Content Detection
--Celebrity recognition
--Text detection
--Rekognition can work on millions of photo.


Question: Give simplest example of working of Rekognition.
Each time a person arrives at your home, your door camera can upload a photo of the visitor to Amazon S3,
triggering a Lambda function that uses Rekognition API operations to identify your guest, and display the data on screen/mobile.



Question: Give some use case for Rekognition?
--Searchable image and video libraries
--Face-based user verification App
--Get the Sentiment and demographic analysis
--Detect the Unsafe Content Detection from photo/video
--Detect the Celebrity recognition
--Get the Text detection From photo/video


Question: What we can get from Rekognition for photos?
--Label detection
--Face detection and comparison
--Celebrity recognition
--Image moderation
--Text in image detection


Question: What we can get from Rekognition for videos?
--Labels
--Faces
--People
--Celebrities
--Suggestive and explicit adult content


Question: Recommendations for Stored and Streaming video?
https://docs.aws.amazon.com/rekognition/latest/dg/recommendations-camera-stored-streaming-video.html


Question: Give useful links for rekognition?

Get understanding
https://docs.aws.amazon.com/rekognition/latest/dg/what-is.html

Run sample code online (Require login)
https://ap-south-1.console.aws.amazon.com/rekognition/home?region=ap-south-1#/label-detection

API Docs
https://docs.aws.amazon.com/aws-sdk-php/v3/api/api-rekognition-2016-06-27.html


Question: What are different type of commands detection for videos.
Labels - StartLabelDetection - GetLabelDetection
People - StartPersonTracking - GetPersonTracking
Faces - StartFaceDetection - GetFaceDetection
Celebrities - StartCelebrityRecognition - GetCelebrityRecognition
Detect adult content - StartContentModeration-GetContentModeration




Question: What are different limitation by video Rekognition?
Video must be available in S3
Video must be H.264 codec.
File format must be MPEG-4 and MOV
Max filesize is 8GB