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.
190 questions
0
votes
1
answer
862
views
Checking whether a PDF contains embedded text
Of course, almost all PDFs 'contain text' in the sense of having text that you can read, but I'm talking here about the difference between those in which that's just a bitmap that only gets ...
- 2,709
0
votes
0
answers
238
views
How to extract numbers from an image of a table/grid of numbers?
Not from a calc or excel cell's, but a screenshot of them. Must be OCR. I've been recommended to use microsoft Power Query or microsoft Powertoys, but I dont know how to install them on ubuntu, I do ...
- 11
-1
votes
1
answer
74
views
How to use the duplex scan and OCR with Epson Stylus Office BX635FWD?
I use an old Epson Stylus Office BX635FWD. It supports the duplex scan. But in the settings of the scan software I don't find any config for the text recognition.
Is it possible / How to achieve the ...
- 1,585
0
votes
0
answers
123
views
Photo OCR to file name
I have a large amount of image files with text in them, I would like to know if there is a way to run an OCR scan and mass change the file names based on the OCR scan details. Windows 10
Thank you for ...
- 1
1
vote
1
answer
417
views
tesseract ocr: why a png image containing computer digits returns me garbage when I ocr it to a text file?
I've installed tesseract ocr 5.3.0 (on Debian 12)
I want to scan and ocr this png file:
When I execute a:
tesseract cp1.png cp1
the output cp1.txt contains unexpected garbage:
y ...
- 215
1
vote
1
answer
523
views
NAPS2 Auto detect image when scanning
Is there any way to detect image. I have HP LaserJet Pro MFP M28 printer/scanner and I have some pictures with different sizes to scan. Can I set up NAPS2 to automatically detect image from whole ...
user275486
0
votes
0
answers
176
views
Digit recognition with ocrmypdf
I would like to get a "5" out of this image using ocrmypdf:
I tried:
ocrmypdf digit.png --output-type none --image-dpi 300 --sidecar side.txt - > /dev/null
But nothing, the sidecar is ...
- 1,510
0
votes
1
answer
139
views
How to OCR high number of images using azure vision without programming?
I have about 500 number of images that I definitely want to OCR these images with Microsoft azure vision.
For some reason, I don't have any access to azure account at the moment.
Can I OCR my images ...
4
votes
2
answers
14k
views
How can I improve the quality of pixelated text in scanned PDF images and convert it into non-pixelated, high-quality digital text?
I have a scanned PDF document containing images with pixelated text. The OCR process has extracted the text, but it appears low quality and pixelated. I want to convert this pixelated text into a high-...
- 41
0
votes
1
answer
771
views
Searching for text in DJVU files through the Windows search panel
I have many DJVU files with OCR in one folder. What should be done or how can I search for words in these files through the search field in the folder (top left)? There is a reference to the DjVuOCR ...
- 1
0
votes
0
answers
231
views
Can I annotate a PDF with gImageReader to make it searchable?
I am using the latest version of gImageMaker (3-2023, Windows 10). OCR works fine.
I use a PDF as source, which is not searchable and just want to add the OCR text to the PDF so it becomes searchable.
...
- 2,135
1
vote
0
answers
2k
views
Fix blurry text in a PDF
I have a PDF containing both text and images. Images are ok, but the text is blurry, with a "pixelated" pattern, very difficult to read. If I copy-paste the text from Adobe Acrobat to ...
0
votes
0
answers
914
views
How can I undo OCR in Foxit?
Optical character recognition (OCR) in Foxit sometimes mess up the font. E.g., before OCR:
After OCR:
How can I undo OCR in Foxit? Ctrl+Z doesn't undo OCR. I use Foxit 11.2 on Windows 10. I made ...
- 26.4k
2
votes
2
answers
390
views
OCRmyPDF cannot convert pages with watermarks
I have some scanned magazines with a pink watermark on some of the pages. I need to ocr them and OCRmyPDF seems to be the right tool for the job. Except that it cannot convert text on top of the ...
- 487
0
votes
1
answer
3k
views
How to make pdf and content searchable again in Onenote
A year ago, I could use the search option in every OneNote documents very efficiently (to be more precise I'm using "OneNote for Windows 10" (software version)), it would find words in pdf's ...
- 111