1

my pdf text is too blurry. so i want to convert it to computer font from scanned image.i already tried increassing quality by adobe/edit/preferences/page display.

my blurry scanned image.

Any OS is acceptable, any price. As many solutions as possible.

2
  • the answer from softwarerecs.stackexchange.com/questions/74571/… or other questions with the tag of ocr may potentially be helpful Jan 17, 2021 at 20:57
  • This image isn't particularly ideal for OCR--looks cropped from a larger source and possibly reformatted. The background noise would also interfere with an OCR process. A commercial toolkit (such as LEADTOOLS -- note I work for this company) likely has image preprocessing sufficient to clean up the image to improve the OCR results. End-user solutions would likely automate this process. Apr 30, 2021 at 13:20

1 Answer 1

1

IronOcr specializes in reading even low quality images like this, even without the need for pre-processing, due to the in-built image optimization filters.

You can then export the result as a searchable PDF.

(WaIm EVery passer-oy not io
sufficient cover is required for th
address and telephone number «
»posed-to have sent the repairme
the premises who has called fc
he name of the company shoul
nently on both their car and th
tools the repairmen bring into th
vount of traffic in the buildine ;)

This is easily achievable in just a few lines of code:

var Ocr = new IronTesseract();
using (var Input = new OcrInput(@"images\image.png"))
{
Input.Deskew();
// Input.DeNoise(); // only use if accuracy <97%
var Result = Ocr.Read(Input);
Console.WriteLine(Result.Text);
}

Supports Tesseract OCR on Mac, Windows, Linux, Azure and Docker.

Disclaimer: Work for Iron Software

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy