Rekognition
Recognition is a deep learning based image and video analysis product. It can look at images or videos and intelligently do or identify things based on those images or videos.
It can identify:
-
Objects
-
Specific people
-
Faces, it can analyze faces for emotion and other visual indications.
-
Text, for example license plates
-
Activities, what people are doing in images and videos.
It integrates with applications via APIs and it’s event driven, so it can be invoked for example when an image is uploaded to an S3 bucket.
It can analyze live video by integrating with Kinesis video streams, allowing facial recognition on security camera footage for security type situations and maybe distinguishing between the owner of a property and somebody who’s attempting to commit a crime.
And one example architectural flow might look something like this: an image containing whiskers and woofy is uploaded to S3. We’ve configured S3 events and so this invokes a Lambda function. The Lambda function calls recognition to analyze the image. Rekognition returns the results and then the Lambda function stores the metadata together with a link to the image into DynamoDB for further business processes.
Pricing is per image or per minute of video.