Questions tagged [ocr]

Optical Character Recognition, the process of converting printed or handwritten text or images of text into digitally encoded text on a computer (so that, for example, it can be reproduced, machine-translated, reformatted, edited, distributed, used as input to software such as text-to-speech and so on)

Filter by
Sorted by
Tagged with
0 votes
0 answers
8 views

PDF Post Processing with Evince (Document Viewer)

I have a scanned PDF document which I've opened with Ubuntu's document viewer (Evince). When I select a part of the text in the document, it automatically processes the scanned text and converts it to ...
user avatar
0 votes
1 answer
52 views

How to install Mathpix Snip in Ubuntu 22.04 using terminal?

I installed Mathpix Snip in Ubuntu 20.04 by following the following instructions from their documentation: Getting Snip app and launching it from your Terminal (Advanced) Open your terminal. And ...
user avatar
  • 1
0 votes
0 answers
19 views

How to do -really working- OCR with a PNG input? only having azAZ09/+=

There is a sample PNG file: it has the following text in it (basic base64 output): jStUrVD/bWG2WfG0SaAbEELlBDNadWTlo4EqsPZPShTdodJ+3ETXSDW8AjkXZSjP08tyJMW/kqTL04+Zz0slLt9pUZ2XGjcFeG4J1P8GvV6UmR9+...
user avatar
1 vote
0 answers
39 views

I'm having trouble installing OCRopy, I want to use it to create train data for an old manuscript in latin. What prereqs are needed and lines to write

So I am new to using Ubuntu and I am trying to install OCRopy to make train data with the end goal of creating a transcript for a 15th c. manuscript. So far I am considering that my problem may be a ...
user avatar
  • 11
2 votes
0 answers
64 views

OCR with two-page layout

I'm trying to do OCR on a pdf with a two-page layout - in a landscape-orientation page of the PDF, the left half is one (portrait-orientation) page, the right half is the next (portrait-orientation) ...
user avatar
  • 121
0 votes
1 answer
1k views

Why does tesseract append ^L to the output

I am using tesseract to OCR some text in images, e.g this one: I have this version of tesseract on my Ubuntu 20.04: $ tesseract --version tesseract 4.1.1 leptonica-1.79.0 libgif 5.1.4 : libjpeg 8d ...
user avatar
3 votes
1 answer
2k views

OCR of a pdf with gocr

I installed gocr, with the command suggested by the ubuntu terminal (sudo apt install gocr), in order to carry out an OCR recognition of the text in a pdf file. How could I use it? I didn't find a ...
user avatar
0 votes
0 answers
129 views

Tesseract with "fl" and "fi" characters

I started using tesseract yesterday. It worked very well, but apparently my original text (in the scanned image) had characters that combine fi into one, single character and fl into another single ...
user avatar
  • 61
0 votes
1 answer
120 views

Cannot install ocrfeeder on Ubuntu 18.04

ocrfeeder is an Ubuntu desktop application which utilises Tesseract and other OCR engines to perform OCR. I had it running OK under Ubuntu 14 but am having problems installing it under 18.04. Problem ...
user avatar
1 vote
1 answer
1k views

Can Qt-box-editor be used for tesseract 4.0?

I am using tesseract 4.0 for character recognition. In many blogs, it is written that Qt-box-editor can be used with tesseract 3.x. My question is:- Can Qt-box-editor be used with tesseract 4.0?
user avatar
0 votes
1 answer
283 views

Is there OCR software for HP Laserjet Pro MFP M130A multifunction printer?

Is there any OCR software available for HP Laserjet Pro MFP M130A multifunction printer? How can I install it? I'm using Ubuntu 18.04.
user avatar
0 votes
3 answers
7k views

Ubuntu 18.04 error install tesseract

I've installed Ubuntu 18.04. I've installed tesseract using sudo apt-get install tesseract-ocr When I type: tesseract -v I had an error: tesseract: symbol lookup error: /usr/lib/x86_64-linux-gnu/...
user avatar
2 votes
1 answer
221 views

Copy+Paste from Screenshot [duplicate]

I receive a lot of screenshots during my daily work. Most of them contain numbers which I need to copy+paste. Is there a magic way to copy+paste numbers from images? I use thunderbird and firefox ...
user avatar
  • 2,372
2 votes
2 answers
1k views

gimage reader OCR

I have recently installed gimage reader OCR. It is not obvious how to use it. I have not yet worked out how to get an editable text file. My aim is to get a libreoffice file to edit and save. Thanks ...
user avatar
  • 21
3 votes
1 answer
2k views

How to create high fidelity PDFs with copyable text from scans?

Some companies provide software for Windows with their scanners* that can create PDFs from scanned pages which look exactly like the scanned material (as if it were just full-page images) but the text ...
user avatar
0 votes
1 answer
1k views

How can I get Tesseract OCR to recognise the large digits of an electricity meter?

I want to use an OCR program on an RPi to recognise the digits from a photo of my electricity meter. The digits are large and are very obvious to me, but Tesseract appears unable to recognise them at ...
user avatar
3 votes
0 answers
1k views

Extract text from image

I am looking for software that recognizes text within images. I tried out all of the tools mentioned here (gocr, fuzzyocr, libhocr0, ocrad, ocrfeeder, ocropus, tesseract-ocr, cuneiform). My input was ...
user avatar
  • 2,181
2 votes
0 answers
727 views

Conversion images pdf to text

I have a 500page pdf scan of a 15th century book. I wish to convert it into a single txt file of any format so as to be able to work on it and/or export it to epub. Calibre is unable to process it. ...
user avatar
1 vote
0 answers
345 views

Why is OCR-Text recognized with whitespaces after every char?

I'm trying to get all my documents scanned and throw away those nasty papers. To simplify this process I recently bought a Brother ADS-2100e scanner. I thought this scanner could create OCR-PDF on USB-...
user avatar
  • 43
-1 votes
1 answer
2k views

pytesseract not working [closed]

Python 2.7.13 (v2.7.13:a06454b1afa1, Dec 17 2016, 20:42:59) [MSC v.1500 32 bit (Intel)] on win32 Type "copyright", "credits" or "license()" for more information. >>> from PIL import Image >...
user avatar
3 votes
1 answer
3k views

How can I use OCR on a partial screen capture to get text?

When I was still using Windows I loved using the capture2text OCR program to grab Japanese kanji from manga and dump them into jisho.org, and was wondering how I could get the same functionality on ...
user avatar
34 votes
1 answer
54k views

How do I install a new language pack for Tesseract on 16.04

Just installed gscan2pdf v1.3.9 as well as Tesseract. As for the latter, first it appeared at the bottom of my Installed Software list, but now it seems to be gone, although still working (I think). ...
user avatar
  • 555
0 votes
2 answers
88 views

Convert hand written data log to excel [closed]

I have to enter loads of hand written data into excel and I was wondering if there is an easier way of doing it than typing all the data into the excel manually. Any suggestions?
user avatar
1 vote
1 answer
222 views

Why ocrodjvu's engine not found?

I run unsuccessfully in Ubuntu 14.04 LTS, trying to have better OCR of a DjVU document ocrodjvu --in-place document.djvu but get ocrodjvu: error: OCR engine (tesseract) was not found. I found out ...
user avatar
-1 votes
1 answer
116 views

Ocr can't recognize a specific image [closed]

I am seeking to make these images , (8,0) recognized by an Ocr I am using tesseract but i don't mind if another Ocr make it
user avatar
  • 641
1 vote
1 answer
208 views

OCR-Software sought

What is recommended commercially free usable OCR-Software? It should be accessible via Python or a Python library. And it should run under Linux. The one I came across myself is tesseract. Are there ...
user avatar
  • 3,633
2 votes
1 answer
3k views

OCRopus installing problem

I'm working on a project and need to use OCRopus, I tried to install it on windows but failed, so I moved to Ubuntu. I'm not a nerdy when it comes to Ubuntu, so I'm stuck now. I have installed python ...
user avatar
  • 23
4 votes
1 answer
2k views

ocrfeeder doesn't detect anything

When I try to detect text on my jpeg, it shows correctly all areas where it suspects text and images, but when I export it to ODT it only creates an ODT with empty text- and imageframes. Do I have to ...
user avatar
  • 30.2k
1 vote
1 answer
927 views

Use xsane as OCR without scanner

When I start xsane, It exits with the message no decvice accessible. But I would like to use it just as OCR tool. How can I suppress the device search?
user avatar
  • 30.2k
0 votes
2 answers
183 views

OCR for TAN list (online banking)

I have a TAN list on paper for online banking that looks like this: 001 123456 015 123456 029 123456 043 123456 ... 002 123456 ... ... I scaned it and now I want to use OCR to get the text. I ...
user avatar
  • 2,372
4 votes
1 answer
1k views

How I prevent hocr2pdf to use a large font from tesseract generated .hocr file?

Tesseract now creates an .hocr file rather than an .html file for ocr output, but this is not exactly what is at issue here. When hocr2pdf uses this output it uses a large text size with small ...
user avatar
33 votes
7 answers
17k views

How to turn a pdf into a text searchable pdf?

I have a number of scanned documents in pdf and I want to be able to search them. How can I do that? Essentially I have to OCR the pdf and then blend the extracted text back into a new pdf. I have ...
user avatar
  • 27.5k
0 votes
1 answer
806 views

Is it a good idea to try to compile tesseract 3.02 on ubuntu 14.04?

I have ubuntu 14.04 on my notebook, and i am going to work with tesseract by compiling it for some computer science related research. Am i on a good path? Svn of tesseract provides only 3.02 as i ...
user avatar
2 votes
2 answers
2k views

Why are no OCR engines working in Gscan2pdf after upgrading to 14.04?

I recently upgraded to Ubuntu 14.04, but the OCR in gscan2pdf stopped working. I am using the latest gscan2pdf (1.2.4) with both Tesseract and Cuneiform available. When loading pdf documents in ...
user avatar
2 votes
1 answer
892 views

scan receipts with a GUI

I'm new to ubuntu, and I'm trying to find an application to scan my receipts in order to create an expense report. Is there any software available? Any help is greatly appreciated. thanks
user avatar
0 votes
2 answers
1k views

Install GimageReader in Kubuntu - my last step of getting rid of Windows

Hope all are doing well. I have been Windows-free for almost two weeks now. And I am not even using Wine, to use Windows software. Initially I installed Ubuntu, then I shifted to Kubuntu [I like the ...
user avatar
  • 31
2 votes
1 answer
1k views

Help with Canon CanoScan LiDE scanned PDF Documents

I have just started working with Ubuntu for the last 10 days, with the intention to stop using Windows permanently. So far it has been awesome. I have replaced almost all my Microsoft applications ...
user avatar
  • 31
1 vote
1 answer
1k views

Tesseract OCR Engine on ubuntu how to

I've installed tesseract-ocr. I was looking at the manual, but i can't see an option that i can define an image bounds (X,Y,W,H) Can someone help about it , or am asking in a wrong place ?
user avatar
3 votes
3 answers
942 views

Is there a good OCR-readable font

As part of my backups, I would like to be able to print and later re-scan a Base64-encoded copy of my private key. Unfortunately, neither gocr nor tesseract seems to be able to properly read any font ...
user avatar
2 votes
1 answer
698 views

ASCII art generator with OCR

What program can turn an image into ASCII-art, but also replace any text with the actual text with OCR. For example, for converting a comic to ASCII art.
user avatar
  • 326
3 votes
1 answer
5k views

How to improve tesseract performance?

By all accounts, tesseract is superb. However, my results are dismal. I need to convert (digital, as opposed to from a book) text that I only have as a png. For instance: 2 3 academics 1 1711 2 ...
user avatar
  • 407
2 votes
0 answers
764 views

Alternative to Paperwork

I am looking for an alternative to the program Paperwork as it is rather complicated to install under Ubuntu. I am specifically interested in finding a way to read dates, prices and other details from ...
user avatar
3 votes
1 answer
693 views

pdfsandwich - how to not change page colour

I am using pdfsandwich but it changes the colour of the pages from colour to black and white. Since I have a document with many coloured pictures how can I avoid it?
user avatar
2 votes
1 answer
1k views

Cannot Scan from Gscan2PDF on 13.10 or OCR with Tesseract

I am having a little bit of trouble with one of my favourite pieces of open source software. I had installed Gscan2PDF (1.0.4) from the Software Centre on my 13.10 64bit machine (clean install from 13....
user avatar
  • 2,063
1 vote
1 answer
235 views

TV channel Identification using Linux C Programming

I need to develop an application which will identify the channel name which is currently running in the Television. I am using Easy CaP Video capturing device to take the video in from the dth set top ...
user avatar
3 votes
2 answers
19k views

Optical character recognition for LibreOffice

I have a paper document. There are more pages containing a table with 3 columns (current number, name and a grade). I scanned it and got 16 jpeg documents. Each jpeg is a scanned page. Now, I need ...
user avatar
  • 31
1 vote
2 answers
3k views

"sh: 1: cannot open /tmp/pdfsandwich4e375e.html: No such file" when using pdfsandwitch [closed]

I tried to add a textlayer to some pdf files in order to make them searchable. This technique is explained in the german Ubuntu wiki: http://wiki.ubuntuusers.de/pdfsandwich . After installing ...
user avatar
5 votes
2 answers
7k views

Abbyy fine reader like application for Ubuntu 13.04

I have a lot of images and what I want to do is to scan those images and get output in ms word file that can be edited later. For Windows, I have Abbyy fine reader. But I don't want to go back to ...
user avatar
2 votes
1 answer
2k views

Conversion of tiff image in Python script - OCR using Tesseract

I want to convert a tiff image file to text document. My code works as I expected to convert tiff images with usual font, but it's not working for French script font. My tiff image file contains text. ...
user avatar
34 votes
7 answers
21k views

How can instantaneously extract text from a screen area using OCR tools?

In Ubuntu 12.10, if I type gnome-screenshot -a | tesseract output it returns: ** Message: Unable to use GNOME Shell's builtin screenshot interface, resorting to fallback X11. How can I select a ...
user avatar
  • 427