Tesseract: Specifying regions of text

ocr tesseract
sashoalm picture sashoalm · Oct 19, 2012 · Viewed 17.8k times · Source

I'm using tesseract-ocr-3.01 to scan many forms. The forms all follow a template, so I already know where the regions/rectangles of text are.

Is there a way to pass those regions to tesseract when using the command-line tool?

Answer

sashoalm picture sashoalm · Oct 23, 2012

I found the answer, thanks to this thread.

It seems that tesseract suports the uzn format (used in the unvl tests).

From the thread:

Calling tesseract with parameter "-psm 4" and renaming the uzn file with the same name of the image seem works.

Example: If we have C:\input.tif and C:\input.uzn, we do this:

tesseract -psm 4 C:\input.tif C:\output

Related questions

image processing to improve tesseract OCR accuracy

I've been using tesseract to convert documents into text. The quality of the documents ranges wildly, and I'm looking for tips on what sort of image processing might improve the results. I've noticed that text that is highly pixellated - …

Read More
best OCR (Optical character recognition) example in android

I want a running example of OCR in android, I have done some research and find an example that implements OCR in android. https://github.com/rmtheis/tess-two and in it there are three projects files... eyes-two tess-two tess-two-test I …

Read More
Tesseract OCR simple example

Hi Can you anyone give me a simple example of testing Tesseract OCR preferably in C#. I tried the demo found here. I download the English dataset and unzipped in C drive. and modified the code as followings: string path = @"…

Read More