Tag Info

Hot answers tagged

16

I have had success with the BSD-licensed Linux port of Cuneiform OCR system. No binary packages seem to be available, so you need to build it from source. Be sure to have the ImageMagick C++ libraries installed to have support for essentially any input image format (otherwise it will only accept BMP). While it appears to be essentially undocumented apart ...


14

There are several online utilities can be used to identify fonts, including: WhatTheFont!, which can automatically match a font in an image you submit to the closest matches in the database; Identifont and Fonts.com Identify Fonts by Sight, where you specify the appearance of the characters in the font to identify the font. These utilities cannot be ...


13

Evernote API has functionality to get text and rectangle where this text is present inside the image. See http://evernote.com/about/developer/api/evernote-api.htm, check out "Evernote Recognition Index XML Format" and functions to retrieve it. Problem is that they don't do traditional OCR ... their OCR algorithm may produce different words for single "word" ...


12

From the MS TechNet site - Changes in Word 2010: Microsoft Office Document Imaging (MODI) MODI provided a common document imaging and scanning solution for Office. It was also the basis of the Fax feature for Office. When MODI was installed, it was the default handler for .tif, .tiff, and .mdi files. In Office 2010, MODI is fully ...


11

Also, Evernote apparently doesn't decide a particular image is equivalent to exactly one word - e.g., Evernote doesn't determine that a particular image is "clue" and is not "due". Rather, it will track both, and a search for either would return the same image. Hence, there's no way to get a full-text equivalent because Evernote isn't deciding what the full ...


9

See if pdftotext will work for you. If it's not on your machine, you'll have to install the poppler-utils package sudo apt-get install poppler-utils You might also find the pdf toolkit of use. A full list of pdf software here on wikipedia. Edit: Since you do need OCR capabilities, I think you'll have to try a different tack. (i.e I couldn't find a ...


8

First you must tweak those images. I recommend a batch tool like XnViewMP which is free and multiplatform. It has a file explorer. Select all your images, then go to Tools - Batch convert. Add actions like I did: Here are my actions: HLS - make it grayscale: Hue: 0 Lightness: 0 Saturation: -127 Levels - lower black level a bit so that the gray noise ...


7

I found this an interesting problem and had a closer look... First, I used the qpdf commandline tool to un-compress PDF data streams so I could better see the source codes of both files: qpdf.exe ^ --qdf ^ from_abbyy.pdf ^ qdf--from_abbyy.pdf qpdf.exe ^ --qdf ^ after_ghostscript.pdf ^ qdf--after_ghostscript.pdf Looking at one ...


7

OCR works by analysing the shape of the letters. It's more likely to confuse the letter "l" and the numeral "1" for example as they are very similar in shape. Lower case "t" and upper case "T" are more different, so as long the letters are clear enough I wouldn't have thought so. Have you got an example where it's done this?


7

I came across this on Lifehacker quite some time back, and it has been one of my top DIY projects ever since. Replace the iPhone with any camera or imaging, and you get a stack of nice high-res jpegs ready for you to OCR with any software, even (urks!) MS Office... ;) Cheap. Effective. DIY. You can't beat an idea like this. EDIT: Comments raised up some ...


6

Not really. Handwriting recognition is a hard problem and the failure to crack this was one of the key reasons that the Apple Newton failed. Palm had to make a pseudo-script called 'Graffiti' in order to recognize it, and that was done one letter at a time on a special pad, rather than written as a script. You could try an OCR program - it might work, but ...


6

I have earlier posted an answer detailing how to use Cuneiform (open source software) to do OCR on PDF files and how to create a PDF file with the recognized text in a hidden text layer "behind" the original image. As far as I know, Cuneiform actually does support Romanian as well. While the particular solution was for Linux, Cuneiform is available also for ...


5

evernote pays a decent sum to the creator of the ocr-stuff OR paid a decent sum to put something working together. thus, i really doubt that they will let you get the extracted text (+ positioning on the image). (could be a business model, to scan other peoples images and provide good ocr :)) so, the answer is: no.


5

If you can convert the PDF pages to images, then you can use any OCR tool you like on them. I've had the best results with tesseract.


5

Google docs will now use OCR to convert your uploaded image/pdf documents to text. I have had good success with it. They are using the OCR system that is used for the gigantic Google Books project. However, it must be noted that only PDFs to a size of 2 MB will be accepted for processing.


5

I have installed the Acrobat 11 (XI) trial in VirtualBox. Acrobat 11 is single threaded. I have also made an external script that starts multiple Acrobat instances (one per CPU core), parallel processes the OCR job and merges the result. A crucial step is to turn on error logging in Acrobat preferences, parse all .log and reprocess any error files. The ...


4

Greenshot has a feature like that, but you need to have Microsoft Office installed. Take a screenshot of the desired area (using the Print Screen key). In the resulting menu, select OCR. The resulting text will end up in your clipboard. As an example, here's the result of me trying it on your post: Sometimes. I find myself typing out a lot of text ...


4

I recommend you to try FineReader, it does support Hungarian (full list of languages it supports is here), and it worked perfectly with both Russian and English languages in my experience.


4

If it's possible for you to sort the documents and photos, I would suggest a 256-color PNG for the documents (you can do this with IrfanView) without dithering, afterwards use PNG Optimizer on the results. If used on scanned documents, they will, without even resizing, shrink from ~20 MB bitmaps to ~400 KB pngs. I have no suggestion for the photos.


4

The latest version of k2pdfopt can either keep the OCR with native PDF output option (-mode 2col) or restore the OCR using its own OCR. Also, running the k2pdfopt output through Calibre, as some have suggested, is not necessary if you use the right settings in k2pdfopt. Edit: v2.x of k2pdfopt, released 3-Sep-2013, will preserve previously OCR'd text by ...


4

You could download the 30 day trial of Adobe Acrobat Pro and use the 'OCR Text Recognition' function ('Document > OCR Text Recognition > Recognise Text Using OCR...'). In the settings dialog, choose 'Searchable Image' as the output style. This will keep the page image but embed the OCR'ed text so the document will be searchable and allow text to be selected, ...


4

The following products were found listed on Internet, but I haven't used them. Online OCR OCR Terminal OCR Terminal is an online OCR service that performs Optical Character Recognition (OCR) on your scanned images and pdf files and renders them into editable and text searchable documents. Free OCR Free-OCR.com is a free online OCR ...


4

There have been several other questions on SuperUser on OCR, which might be worth checking out for possible solutions. Most notably this answer by Molly looks promising: I really like TopOCR, certainly a great addition to your scan tools: Incredible OCR accuracy, upto 99.8% with a 3 MP camera No page limits, and no extra downloads or ...


4

Given that the OCR has converted: Als Arbeitsmarkbehörde ... to: AlsArbeitsmarktbeh6rde ... A couple of things spring to mind. Try scanning at a higher dpi. It looks like it can't recognise the space between the words, a higher dpi might improve that. Can you set the language of your OCR program? I see that it's converted the "ö" to a "6". ...


4

Office 2007 features Microsoft Office Document Imaging which, while it is not the best OCR software in the world, will at least be able to get back the majority of your documents. If it is not installed then you may need to reconfigure your office setup to add it in. On my system the tool is Found at Start -> Microsoft Office -> Microsoft Office ...


3

In Omnipage 16, 17, 18, you can (better layout): select zone types automatic or by hand adjust the seleted zone type, text, picture, table rotate pages change double pages into single pages export to pdf with and without original scanned image (clearer, easier to read) The program does on demand (better recognition). straighten pages straighten lines ...


3

I think Tesseract is the best (free) command-line based OCR software. Unfortunately there doesn't appear to be a Windows 7 64-bit binary available so you'd have to compile it yourself; here are the instructions for doing so (taken from a comment on the Tesseract FAQ page): Download tesseract 2.04. Unpack it. In this example I've unpacked to ...


3

Unless you have a automated scanner, it would probably be quicker and less effort on your part to type the lotto numbers in by hand. If you do this a lot and want to justify your effort: Buy an automated scanner, with some sort of feeder. Hopefully scanner will dump all the scanned files into a destination folder. Run a script that will trigger OCR on ...



Only top voted, non community-wiki answers of a minimum length are eligible