Questions tagged [ocr]
Optical character recognition (OCR) is the process of converting images of text to text that can be manipulated by word processors etc.
180
questions
0
votes
1
answer
57
views
ffprobe OCR of a subtitle stream
I have some video files containing HDMV PGS subtitles, and I need to convert them to subrip (or other text subtitles). I know that I can ffmpeg demux the video file to extract .sup and on the fly ...
- 83
0
votes
0
answers
8
views
Multipage tiff to a combined hocr output [migrated]
Iam looking for the option to process multipage tiff image to single HOCR file. A combined output of multipage tiff.
At present Iam getting HOCR as different hocr pages.
from PIL import Image
...
0
votes
0
answers
15
views
Extract "content" from json file to avoid metadata
I have hundreds of files of newspaper pages that have been OCR-ed. To analyse them I have to get around all the metadata they include. What is the simplest way to remove metadata from these files, or ...
- 1
0
votes
1
answer
145
views
Getting output only from 1st page TIFF to hocr extract
[Sample Image]
I seek your guidance in the code given below. Iam running this code to extract text from multipage TIFF to hocr format. Iam getting an output from the 1st page of TIFF but rest of the ...
0
votes
1
answer
64
views
Is there a convenient solution to go from PDF to excel?
I receive these god awful invoices in the form of faxes. We are in the process of implementing EDI however this is how it has to be done for the next few months. The employee i have entering the data ...
- 3
0
votes
1
answer
91
views
Print a PDF to a new PDF from Acrobat preserving the ocr text
I would like to print a protected PDF file in another PDF file using Acrobat, so that I can also consult it in the future, and I would like to keep the text searchable: is there a way to do this with ...
- 101
0
votes
0
answers
33
views
Greenshot OCR output save to TXT file
HI guys i was wondering if anyone could help me, i love the simplicity of greenshot for quickly saving snippets, but i was wondering if there was a way of saving the OCR output to a text file on my ...
1
vote
1
answer
69
views
Apache Tika: Where to place tika.xml to disable OCR
I am running Apache Tika to extract text from a bunch of MS Office documents. My command looks like this:
java -jar "c:\path\to\tika-app-2.0.0.jar" -t ...
(I am running this command on Win10 ...
- 353
0
votes
1
answer
35
views
Add an OCR layer over MS Word images (extracted from PDF)
I'm working on a PDF (that i created with LaTeX) and I need to convert in into a MS Word document, but keeping the *exactly* original typesetting and design.
Since all the converters from PDF to Word ...
- 1
0
votes
0
answers
53
views
delete image layer in pdf and work on text layers only
I have a searchable pdf document. I would like to delete the image layer to work on the text layer only. How can I do it? Thanks in advance to those who will help me
- 13
0
votes
0
answers
122
views
How to OCR this subtitle?
Is there any Linux OCR tool that can extract this subtitle without having to train a LSTM? Language is Portuguese. Some image cropping and python coding is acceptable...
I could not find a Tesseract ...
- 300
0
votes
0
answers
30
views
How to mark paper documents before scanning to simplify OCR sorting?
My business generates a lot of handwritten notes that get scanned and sorted into clients' files. Each file has a unique 5-digit numeric code, which is handwritten on the page before scanning. Our ...
- 432
0
votes
0
answers
20
views
How to pre-process the background of this image in order to OCR the table properly?
I have to OCR the book of tables consisting of 500+ pages but the maker stamped every page. Can anybody help me on how should I process it in order to be able to recognize it let's say in FineReader? ...
- 127
23
votes
3
answers
9k
views
Blurry text in PDF
I have a pdf that has blurry text. The text itself is readable but causes lots of strain.
This is an example of the text.
Is there a way to clear it up?
- 241
1
vote
0
answers
205
views
How to OCR the hardcoded Korean subtitles from a movie?
I got a Chinese movie called "Xin li zui (2017)" with Korean subtitles, burned into it. Or, 'hardcoded'. Now, with an French, Spanish or English subbed movie or just any movie which uses the ...
- 41
1
vote
0
answers
318
views
OCR a table to csv using a GUI for tesseract? [closed]
I want to OCR 20 pages of tables to CSV or similar format, using a GUI.
For this purpose I installed tesseract (including tesseract-training and the applicable language package) using MacPorts. I also ...
- 552
1
vote
2
answers
3k
views
Pattern matching in bash to use in case-statements (instead of regex)
I have coded one of my first bash scripts. My goal is to make my office "paper-free". I have a lot of scanned documents, that I want to save with the date (usually found at the top of each document) ...
- 11
0
votes
1
answer
35
views
Copy text from scanned pdf
I have some scanned documents, which I want to copy the text from.
Adobe Acrobat Pro recognizes the text, however it is placed in a bunch of bounding boxes, making it impossible (?) to just mark all ...
- 930
-1
votes
1
answer
244
views
How can I OCR the text from specific regions of a screenshot, then output that to a usable format?
I'm trying to automate logging of uh, ranked games in Street Fighter of all things - Yes, nerdy, I know. I have a spreadsheet
In that I manually put in the following for each ranked game:
The ...
- 99
0
votes
0
answers
59
views
How can I scan and get a PDF file with selectable japanese text?
I have several magazines in japanese. I would like to carry them to read in an airplane but they are too heavy so ideally I am thinking of scanning the pages and carrying them as pdfs. But I like to ...
- 602
1
vote
0
answers
153
views
Manually adding Searchable Words in PDF
Is there a way to add searchable tags/keywords to a PDF document?
I have heard of the OCR option in Adobe Acrobat, but for some reason this program keeps crashing, are there any alternatives?
Can ...
1
vote
1
answer
6k
views
How do I train Tesseract for a new ttf font?
I am trying to train Tesseract for some funny looking fonts, like Palace for example.
I have tried a simple way - produced traindata with
http://trainyourtesseract.com/
and then have made a call ...
1
vote
0
answers
49
views
Is it possible to OCR (frame-by-frame) digital time and multimeter reading values from a video? [closed]
I have a time-lapse video that I need to collect data from (digital time and multimeter reading). Is anyone aware of any apps that can perform this kind of OCR?
The clock and multimeter screens are ...
- 229
5
votes
0
answers
266
views
Can I tinker with the encoding when using pdftotext to convert PDF to text?
Sometimes when I do pdftotext it results in perfect text. I assume this is because the actual unicode text data is embedded directly in the PDF itself, and simply read out.
But other times (around ...
- 289
2
votes
0
answers
391
views
Tesseract: OCR hex and binary strings from old documents
I have some questions about Tesseract
Context
I am currently working on an old cryptographic algorithm from East Germany (GDR) which was developed in the 80s. I implemented the algorithm in C#. Now ...
- 21
1
vote
0
answers
33
views
Specify font when performing OCR
I have a folder full of images that I need to convert to text. Each one contains a string of numbers and spaces on a single line. The images are computer-generated (i.e. not scans with extra ...
- 11
1
vote
0
answers
26
views
UltraVNC fails with OCR, RDC succeeds
I am trying to use OCR on a remote machine, which can be connected to via either RDC or VNC.
There is one script that is supposed to run there, that is using tesseract OCR package.
For some reason ...
- 11
1
vote
1
answer
488
views
What computer specs/ hardware will speed up my Adobe Acrobat OCR speed? [closed]
So, I have a work task where I am Sanitizing the PDF, then watermarking it, OCR-ing it, and password protecting it.
Especially the OCR seems to just take forever, and I'm doing this task on ...
- 11
5
votes
2
answers
733
views
How to leave pdf image unchanged while adding OCR to a pdf with pdfsandwich?
I am trying to add OCR to PDFs and am using pdfsandwich to do so. The problem is that pdfsandwich processes the image when doing OCR which changes what the document looks like.
Is there any way to ...
- 81
1
vote
0
answers
77
views
Google OCR - just in Lens, or can I find it elsewhere? [closed]
I need to convert some screenshots of spreadsheets to actual data. Google Lens seems pretty good at this - I save the image on my phone, then open it up with the Google Lens app, let it do it's thing,...
- 419
0
votes
1
answer
599
views
How to compare multiple PDF files?
My professor just uploaded an updated set of all the slides of the whole semester (17 PDFs), referring to them as the now definite examination material.
Problem is, I have made lots of notes on the ...
- 103
0
votes
1
answer
3k
views
Autohotkey to search images
I'm learning how to use autohotkey and I wanted to create a script which open a game from steam and joins automatically to a specific server. My code so far is:
F1::
Run, steam://rungameid/346110
...
- 103
2
votes
1
answer
1k
views
Would extracting hard-coded subtitles like this work?
I have an mp4 with hardcoded subtitles and I want to make an SRT file.
I tried using the video OCR software AviSub. It got the timings right but the words itself were very innacurate, so I got an SRT ...
- 21
33
votes
4
answers
12k
views
How to create PDF with scanned pages but selectable text?
Today I recieved a PDF from our supplier and it contained several printed and scanned pages with signatures etc. I opened it in Acrobat Reader DC. But to my surprise the text from the evidently ...
- 3,481
2
votes
1
answer
78
views
What's the best method for JPEG text manipulation?
I have a relatively simple graphic; a technical diagram with various bits of text throughout.
The text is in another language (Czech/Slovak). It's printed clearly enough to be accurately ...
- 2,501
5
votes
2
answers
17k
views
Understanding OCR options in Adobe Acrobat: "Searchable Image", "Searchable Image (Exact)", and "Editable Text and Images"
In Adobe Acrobat (I'm using Pro DC if that matters), there are three options for OCR:
"Searchable Image".
"Searchable Image (Exact)".
"Editable Text and Images".
What are the differences between ...
user293098
0
votes
0
answers
863
views
How to use Onenote 2016 as an OCR on a PC
*Note I'm using a PC for all this.
I am trying to take text out of a screen shot made on my computer and when I've tried the methods suggested by the video and the article listed; I don't get the ...
- 103
1
vote
0
answers
35
views
Extract Text From Images,ocr
Extract Text From Images?i have many images,i searched and found some online convertors but doesn't work becouse i have 10.000 image,so i need a mass tool,can someone help me with this,thank you
1
vote
0
answers
305
views
How to OCR document with table and export to text (with proper left/right/top/down text)?
I have a document with many pages that have columnar tables like the following.
#1 2.1 This is some text. It can go onto the next line
like this.
#2 1.3 More text.
#3 3.2 And some more ...
- 2,195
-1
votes
1
answer
584
views
How can I convert a .png image to .pdf with OCR text? [closed]
I have a .png file that is a screenshot of an article I found online. I would like a PDF version of it, with all the text selectable.
Are there any apps or tools that do that?
- 595
1
vote
0
answers
96
views
Extract PDF Data using categorized annotations
Are there any existing tools to extract data from PDF files using this method.
Lets say I have 3 categories
Image - this will be a rectangle annotation which will crop that specific area where the ...
- 163
0
votes
1
answer
1k
views
How to extract text from an image-based pdf using Cuneiform in terminal
cuneiform -l eng -f text -o outocr.txt input.pdf
The above command, when run in terminal, outputs only the text of my PDF title page to the outocr.txt file. What should I do to make it recognize ...
- 1,548
1
vote
3
answers
7k
views
How can I convert PDF bank statements to a Excel or CSV file?
I am just doing my UK tax return (Yes I have left it until the last minute). My bank (Nationwide) will only let me download the last 15 months of transactions as a CSV file, but will let me download ...
- 1,303
3
votes
3
answers
2k
views
How to effectively scan 130,000 paper pages in 10 days
I have a rather large project which will ultimately benefit society, and I'm looking for all the help I can muster.
I have about 130,000 pages that need to be digitized. Many of them are in packages ...
- 398
0
votes
3
answers
52
views
Capture text on page with background white from photography
I intend convert a photography, with txt on page with background white, to txt file. The purpose is capture all text on this images.
I google and I founded the imagemagick and this tools: SCAN Image ...
- 111
0
votes
1
answer
968
views
Can I "roll back" to the PDF without OCR?
I'm using Automator in combination with Abbys Finereader to watch a Folder for new scanned PDF documents. The Finereader OCRs the Document and exports it to a new PDF in the same Folder. For a month ...
- 1
2
votes
2
answers
1k
views
Adobe could not perform recognition: This page is larger than the maximum page size of 45 inches by 45 inches
I tried to run the text recognition tool in a PDF, and obtain the following error message:
Adobe could not perform recognition (OCR) on this page because: This page is larger than the maximum page ...
1
vote
1
answer
240
views
OCR on pages containing both text and images in Acrobat XI Pro
Why does Acrobat XI Pro not allow an OCR scan on pages containing both images and renderable text? The sample PDF in the screenshot was created from an MS Word doc. The first line was typed out; the ...
- 2,458
-1
votes
1
answer
536
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,...
- 372
2
votes
0
answers
212
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 ...
- 372