Return text from image with high accuracy

Question

1.00/5 (1 vote)

See more:

HI Friends
I have code that returns the text in the image by Tesseract OCR.

But the accuracy of the resulting text is not acceptable at all!
I will attach the my photo. return text is :'EPVWUAG2LOSCBPZAANIZZ10 1'
Please guide me how to get the text more accurately

MY IMAGE t5 — Freeimage.host[^]

What I have tried:

VB

Dim api = OcrApi.Create()
 Using api
 api.Init(Patagames.Ocr.Enums.Languages.English) ' Languages.English)
 Dim plainText As String = api.GetTextFromImage(PictureBox1.Image) '(bmp)
 Dim lines As String() = plainText.Split(New String() {vbLf}, StringSplitOptions.None)
 TextBox1.Text = lines(0)
 End Using

Posted 2-Dec-22 13:15pm

moshaveran

Updated 2-Dec-22 17:29pm

PIEBALDconsult

v2

Add a Solution

Comments

PIEBALDconsult 2-Dec-22 19:38pm

Hire an MBA, they need the work.

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Dave Kreskowiak · Answer 1 · 2022-12-02T13:57:00

Solution 1

More accurately? Well, the source image you posted is pretty bad, so I doubt you're going to get acceptable accuracy with ANY OCR package.

Your only options are to try various OCR packages to see if they can do a better job, or write your own OCR library and train it with a fairly large set of images and known return values.

Do I have examples of doing that? No.

Posted 2-Dec-22 13:57pm

Dave Kreskowiak

Comments

moshaveran 3-Dec-22 2:18am

thanks from answer. If you have time, visit my new post and helping me
https://www.codeproject.com/Questions/5348693/Extract-text-from-a-rectangle-area-of-a-PDF