Optical character recognition (OCR) is the process of converting images of text to text that can be manipulated by word processors etc.

learn more… | top users | synonyms

1
vote
2answers
200 views

What is this symbol `¬` and how to remove it from a ms word 2013 file?

I used an ocr program to convert some scanned pages to an ms word file. After the conversion is possible to found the symbol ¬ in the middle of many words. I tried to search and replace it but word is ...
1
vote
2answers
2k views

How to search a PDF where text is just image?

A PDF needs to be searched for text but it is just an image so it's not aware of the characters. I've been trying to do OCR to the PDF but am not skilled in the programs required. I tried Foxit Reader ...
3
votes
1answer
2k views

In Onenote, how do I 'make text in image searchable' enabled by default?

OneNote has a great OCR feature where you can select an image and click make text in image searchable. But I'd like this enabled by default for all images I paste into OneNote - is this possible? (...
3
votes
1answer
688 views

Replace (OCR) garbled text in PDF?

Now and then I come across a PDF which looks fine in first place but the underlying text is garbled. Currently I have a PDF where only the headings are garbled and I would like to know if it's ...
3
votes
1answer
558 views

How to add OCRed text to original pdf in gscan2pdf?

I am new to gscan2pdf 0.9.31, and just used it to OCR a scanned pdf. After saving the pdf, the OCRed text is stored on the top left corner. However I wish each OCRed character to be added to ...
3
votes
1answer
2k views

Training Tesseract-OCR for english language fonts

I have about 3000 small images of single words that I am trying to convert to text. I have installed tesseract on my windows 7 machine using the installer and successfully managed to OCR images ...
2
votes
1answer
174 views

How can I port a text layer from one PDF to another? (in windows)

I have a few files in .djvu format, which size is small, but unfortunately mi e-reader can't display it. I use DjvuToy to transform it to PDF and it keeps the small size; but then, when I use Abby ...
1
vote
1answer
116 views

OCR PDF Parse selected area

I have many account balance documents, I need to create an Excel file from a table inside these documents. I can proceed with a normal OCR recognition but the main problem is that these PDFs have page ...
1
vote
1answer
506 views

Scanning, OCR and adding the scanned numbers

I need to scan hundreds of pages with numbers written on them in the bottom right corner. Post scan - I need a OCR software to recognize the number written at the bottom right corner of each page and ...
1
vote
1answer
242 views

Identification software for Mathematical symbols?

Typically if you've forgotten or have never seen a symbol in a math equation before you are forced to read a large part of the context you found it in and guess which name that symbol has. That is too ...
1
vote
1answer
707 views

Apply metadata to files based on OCR of their content

Essentially I'm looking for a tool (Windows/Mac) that will allow me the following workflow: Scan ALL my documents into a folder (200-300 scanned images) run the tool that will go through all the ...
1
vote
1answer
991 views

Tesseract OCR - Newbie Questions!

I just installed Tesseract OCR and was able to convert a TIF image to its corresponding text. The application seems fairly easy to use, but I am struggling finding the documentation that will help me ...
0
votes
1answer
23 views

Compare documents (images)

I need to compare a pdf with about 27000 pages (scanned pages) to another pdf with about 28000 pages (also scanned pages) so that I can find the 1000 pages which differ. Does anyone now a good ...
0
votes
1answer
221 views

In jTessBoxEditor for Tesseract how to combine multiple TIFF/boxfile into one traineddata file

I think this would be possible with command line, but how to do it with jTessBoxEditor as it would automatize a lot of workflow. Since jTessBox supports multi page TIFF I think that might be the way,...
0
votes
1answer
138 views

Convert text in image file to text file

I have a PDF file which is a scan of a form containing pictures, tables and text. I'd like to run a program (not an online tool) on the file and have it produce a txt file containing the words. Not ...
0
votes
1answer
41 views

auto-folder documents with templates

I have about a million documents I need to move to new folders based on their content. I'm looking for a tool where I can give few samples and the program would find similar documents and move them to ...
0
votes
1answer
121 views

gImageReader Clipboard doesn't work on Windows

I'm using gImageReader to do some OCR on Windows 7, and though I can copy from within the application itself, I can't copy to the external Windows 7 clipboard. I believe the program is gtk based, and ...
0
votes
1answer
2k views

Stripping Non-Text from a Scanned, OCRd PDF

I have a PDF created from a scanned document. OCR was used to recognize text. In Acrobat, if I select text, and click 'copy with formatting', I can paste the formatted text into Word, so it seems that ...
0
votes
1answer
1k views

Image Post-Processing : Unpaper

I try to make Unpaper to work, it's a very powerfull tool to post-process scanned book pages. I read the Doc but still can't make it work neither on Windows nor on Linux. My picture is a Bitmap I ...
0
votes
1answer
726 views

OCR batch processing images

I have about 3000 small images of text which I want to process into a comma separated list. Is there any free program that would be capable of this?
0
votes
1answer
911 views

I have scanned a bunch of receipts and I want to scan/OCR their data into an excel file. How would I do this?

All the receipts have the same layout (i.e. their order list, transaction dates). I was wondering if my OCR program (Omnipage 17) could go to a certain co-ordinate and recognize the data, then some ...
0
votes
1answer
737 views

OCR for Sanskrit ( OR devanagari)

I need an OCR s/w for Sanskrit OR devanagari. I need a s/w which can convers character into UNICODE.
-1
votes
1answer
20 views

OCR messed up by Ghostscript

Last year there was a bug found in Ghostscript. It is documented here: http://bugs.ghostscript.com/show_bug.cgi?id=696116 It is marked Status: RESOLVED WONTFIX In the end the assignee, Ken Sharp,...
2
votes
0answers
73 views

Funny OCR-situation

I have a multipage scanned 300 dpi PDF-file on an Ubuntu 16.04 system. When I run the following command: pdfocr -t -l swe -i *.pdf -o newfile.pdf It results in a perfectly OCR-read file. Every ...
2
votes
0answers
36 views

Converting Multiple .doc files to searchable .pdf

I have a batch command file that runs daily converting data extract files to .txt, .doc, and then to .pdf formats. I run a series of formatting macros in Word on the .txt file before saving to .doc ...
2
votes
0answers
56 views

DjVu hidden text → PDF?

Is there a way to make a PDF of only the hidden text layer of a DjVu file? I know how to use djvused myfile.djvu -e 'output-txt' > myfile.dsed to output a DjVu script that includes the x,y ...
2
votes
0answers
188 views

Tesseract can't scan `Error:Only 1,2,4,5,6,8 bpp are supported:32`

Even though I did convert canvas.png -depth 8 canvas.tif I am still seeing this error message: Tesseract Open Source OCR Engine check_legal_image_size:Error:Only 1,2,4,5,6,8 bpp are supported:32 ...
1
vote
0answers
24 views

How can I get an image of text transcribed where I can specify the font (TFF file)?

Is there possibly some way to quickly transcribe a large amount of text in a weird font (i.e. something like BulletMix: https://www.fontstock.net/4041/bulletmix.html)? I have access to photoshop, but ...
1
vote
0answers
210 views

Turn Off Dictionary in Tess4J

The accuracy of character recognition in my tess4j OCR application is very low. I have heard that turning off the dictionary in tess4j will increase the accuracy by letting individual characters to be ...
1
vote
0answers
164 views

OCR by setting font

I have some images which have fonts like Lucida Handwriting. Since those are cursive my OCR Software doesn't recognize them correctly. Is there a way to let the software to know that the fonts in ...
1
vote
0answers
423 views

Applescript + pdfpen for ocr on multiple files: how to move on when pdfpen freezes

I'm using the following AppleScript to batch-process pdfs for ocr: tell application "Finder" set target_folder to target of front Finder window repeat with i from 1 to count (every folder of ...
1
vote
0answers
549 views

What are the possible tools to convert from pdf to epub?

I know similar questions have been asked before, but before marking it as duplicate, let me explain. I just bought a .pdf ebook online and would like to have it as a .epub instead. I usually use ...
1
vote
0answers
142 views

Batch-OCR screenshots and save their content in metadata?

For quite some time, I've been looking for a way to make screenshots searchable on my mac. Is there a way to batch-OCR them and then save the text with the image or index them in some way, so ...
1
vote
0answers
515 views

How can I preform OCR from the command line?

I need to perform OCR on the a backend of a website on a Linux machine with printed text. I read the other related questions here, so I tried tesseract, wich is considered as one of the most accurate ...
1
vote
0answers
249 views

Scanning low resolution images with Omnipage OCR

I tried scanning with Omnipage OCR (version 17) a relatively lower resolution image of a document that I took with my mobile phone. This document was intentionally not scanned (for future training ...
0
votes
0answers
117 views

How to compress Tesseract-encoded PDFs while maintaining embedded text from OCR?

I've been experimenting with using Tesseract to OCR my PDFs, and it has been mostly successful, particularly with German Fraktur texts (the old style gothic print), which tools like Adobe Acrobat can'...
0
votes
0answers
17 views

Change Trade Manager software language

I have installed Alibaba Trade Manager software. Unfortunately it in Chinese language. How to make its interface English? This is its settings window:
0
votes
0answers
53 views

Convert and compress multiple tif (image) files into one PDF with OCR

I have found one old project that does exactly what I want! But it's broken somehow. Some crucial parts seems to be missing. It's a nightmare to configure. You can look at it here: http://...
0
votes
0answers
26 views

Scheduled batch OCR scanning with Adobe Acrobat XI Pro

I have setup a Batch Process in Adobe Acrobat XI Pro and I was just wondering if it was now possible to schedule this batch to run? I have read some old posts that this was not possible, but nothing ...
0
votes
0answers
70 views

How to determine automatically if PDF file is scanned andn does only contain images (no text)

I have several hundred pdf files which are mostly scanned documents (with no text layer). I want to do an OCR, but before I want to filter out those which do already contain text. I'm not sure how I ...
0
votes
0answers
38 views

Is it possible to unprotect a copy protected PDF by recovering the character mapping using OCR?

There is a certain way of restricting the ability to copy text from a PDF which works by mapping each character of the used fonts to random characters of the so called private area of the Unicode ...
0
votes
0answers
16 views

How can I fix a typo I inserted when correcting an OCR suspect?

I inserted a typo when I was correcting an OCR suspect in Acrobat Pro XI. I saw my error just as I clicked "Accept & Find." Where/How can I fix it? Thanks
0
votes
0answers
56 views

Changing OCR parameters in OneNote 2013

If I insert at PDF file (Print to OneNote) and then perform OCR using Japanese as the OCR language, OneNote will insert a Western space between characters. As an example 河合継之助 will in the OCRd text ...
0
votes
0answers
62 views

Why does performing OCR in Adobe create a much larger document?

I'm using Adobe Acrobat Pro XI on Macintosh OS X Yosemite and I've noticed that doing OCR sometimes creates a much larger document. For example, I scanned a four page document and got a 458K document,...
0
votes
0answers
106 views

OneNote 2013, OCR, imported/printed PDF, reset picture to original size, it highlights wrong place

The title is messy, sorry for that. My point is that if I use the "Send to OneNote" feature, and then right click the print out and choose "restore to original size", the text OCR search will be off-...
0
votes
0answers
101 views

nike ocr twitter api rsvp software not working

I recently purchased an OCR program that reads through Nike's Twitter page and takes a circled word out of a picture and sends it back in a Twitter DM. However, it recently stopped working, probably ...
0
votes
0answers
82 views

Are there any program for showing tooltip via OCR

Edited for clarification based on comments: At work we have an old developed program where I need to navigate on a very long dropdown list only with numbered codes. To select the correct code, I ...