Ensemble OCR

Introduction

This use case demonstrates how deep learning algorithms can be applied in OCR, to extract the information contained in a scanned image. These images consist lines, tables, and text information.

Problem Description

Most organizations (e.g. Bank) receive large number of scanned documents that need processing, often done manually.

  • Manual processing needs lot of time and resources, and hence expensive
  • Manual processing is prone to errors

Using AI (OCR) to automate document processing resolves this problem

Video Walkthrough

How to setup in platform

Coming soon


Concepts to know