Serverless Cloud OCR

by Steve JeffersonSept 8th, 2016

Summary

  • Serverless Cloud Document Reader is a Django application that integrates Microsoft AZURE, Amazon Web Services and Zappa to deploy a Cloud Optical Character Recognizer utilising serverless computing.
  • Intelligent management of resources, server deployed using function as a service (FaaS) principles.
  • This project was developed by Steve Jefferson and is released under the MIT License.
Github

Features

  • Text recognition
  • OCR (Optical character recognition)
  • ICR (intelligent character recognition)hand-printed text
  • Supported file formats: JPEG, PNG, BMP, and TIFF
  • Detects the image orientation and correct it before further processing (e.g. if it's upside-down).
Example of the OCR being run on this pan card image sample

License

This project was developed by Steve Jefferson and is released under the MIT License.