Quickstart
I have several use cases that require either text or image processing. One use case involves processing weather radar images along with metadata and textual weather statements around the 6-10 min intervals - towards the goal of extreme event forecasting (essentially tracking the purple pixels as they move between radar sites).
see Weather Radar Prediction
see AWS Event Driven Architecture
AWS Text and Image Processing
DevOps
Use Cases
Ideally a use case involving hand written answers to tabular forms.
AI-2 - Getting issue details... STATUS
see SBI in AWS Comprehend https://docs.aws.amazon.com/comprehend/index.html?id=docs_gateway#lang/en_us
AWS Feasibility using Textract
Textract Finops
| free tier | For the first three months after account sign-up, new customers can analyze up to 1,000 pages per month using the Detecting Document Text API and up to 100 pages per month using the Analyze Document Text API. |
| API | $.07 per TX - FinOps#CostingFormulas |
Textract Limits
Textract Initial Infrastructure
https://console.aws.amazon.com/textract/home?region=us-east-1#/
Textract API
https://docs.aws.amazon.com/textract/latest/dg/analyzing-document-text.html
Textract API Examples
| API | Use Case | Example |
|---|---|---|
| Console | UTC time extraction from Weather Radar Image | |
| CLI | biometric:ai-cloudformation michaelobrien$ aws s3 ls textract-console-us-east-2-88e8126b-8081-4ebb-8aaf-1e2158be1a28
2021-04-06 11:50:54 56550 xft_2012_06_03_17_00.pdf
asynchronous
biometric:openshift michaelobrien$ aws textract start-document-analysis --document '{"S3Object":{"Bucket":"textract-console-us-east-2-88e8126b-8081-4ebb-8aaf-1e2158be1a28","Name":"xft_2012_06_03_17_00.pdf"}}' --feature-types '["TABLES","FORMS"]' --region us-east-2
{
"JobId": "e4176abc8ff644736ef778d37b746b4b8dd295358acb04a00bcfd2a45642c6e7"
}
| |
DynamoDB tracking
