1

I wanted to extract data from PDF which has image, and the image is form where letter will be inside small boxes for example, name : t e s t, here each and every word will be inside square box.

I have tried tesseract OCR could not get the desired result.

I have tried commercial ABBYY worked but I wanted to use java based free API.

below is the example enter image description here

Grant Foster
  • 722
  • 2
  • 11
  • 21
raghavendra prasad gudipalli
  • 193
  • 1
  • 10

3 Answers3

2

Nicomsoft OCR SDK which is a free SDK has extracted the text from my PDF and results are satisfactory

it supports really large technologies, Now I am trying to integrate it into my application

Link https://www.nicomsoft.com/

raghavendra prasad gudipalli
  • 193
  • 1
  • 10
0

As far as free goes in OCR, Tesseract is as good as it gets.

Alternatively you could look at the Windows 10 UWP OCR offering.

fistynuts
  • 306
  • 2
  • 8
0

I am not sure about the free ones out there, but you can definitely try TotalPDFConverterOCR

It has wide range of things like converting to doc,images etc.

nashcharles
  • 1