Take the 2-minute tour ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

I've used SimpleOCR, which has a nice GUI for correcting mistakes. Unfortunately it makes a lot of mistakes! (and suffers other bugs and limitations)

On the other hand Tesseract is more accurate but has no GUI at all.

My question is, is there a free OCR program for Windows which has a nice GUI and a low error rate? I want it to highlight suspect words (by OCR uncertainty, not just spell checking) and show the original (bitmap) word while I'm editing the OCRed word similar to what SimpleOCR does.

Open-source would be best, followed by freeware, then trial / demo / crippleware a long way behind.

SimpleOCR screenshot showing GUI for correcting errors

share|improve this question
    
possible duplicate of Free OCR software –  Sathya May 16 '10 at 3:10
2  
@Sathya: my specific requirements differentiate it from that question. –  Hugh Allen May 16 '10 at 4:03
    
Not exactly free, but have you looked into Microsoft Office? It comes with OCR. (Look for "Microsoft Office Document Imaging" feature in the setup.) –  horsedrowner Aug 16 '10 at 9:03
    
@horsedrowner: I just tried it. Its accuracy is comparable to Tesseract but it requires a TIFF file with appropriate DPI setting or it doesn't work, and it has no interface for correcting OCR mistakes. –  Hugh Allen Aug 16 '10 at 15:52
    
@Hugh Allen: Does it? It worked pretty well when I stumbled upon the context menu function in OneNote 2007. And I was using a random image file copy-pasted from a website... –  horsedrowner Aug 16 '10 at 21:11

3 Answers 3

Have you tried gimagereader , a gui front for Tesseract ?

share|improve this answer
    
I just tried it (under Windows) and it doesn't run for me - the process exits immediately without an error message :( Anyway looking at the screenshots it doesn't appear to actually highlight the word you're editing. Have you tried it? –  Hugh Allen Aug 16 '10 at 14:37

OCRopus:

The software is partly based on Tesseract, the best open source OCR engine available for now. While the project is expected to be released at the end of next year and will be used for Google's book scanning project, the team has some interesting applications in mind:

  • a web service interface
  • PDF, camera, and screen OCR
  • integration with desktop search tools: Beagle, Spotlight, Google Desktop

OCRopus(tm) is a state-of-the-art document analysis and OCR system, featuring pluggable layout analysis, pluggable character recognition, statistical natural language modeling, and multi-lingual capabilities.

The OCRopus engine is based on two research projects: a high-performance handwriting recognizer developed in the mid-90's and deployed by the US Census bureau, and novel high-performance layout analysis methods.

OCRopus is development is sponsored by Google and is initially intended for high-throughput, high-volume document conversion efforts. We expect that it will also be an excellent OCR system for many other applications. alt text Links:


GOCR

GOCR is an OCR (Optical Character Recognition) program, developed under the GNU Public License. It converts scanned images of text back to text files. Joerg Schulenburg started the program, and now leads a team of developers. GOCR can be used with different front-ends, which makes it very easy to port to different OSes and architectures. It can open many different image formats, and its quality have been improving in a daily basis. alt text alt text

Links:


share|improve this answer
    
Do either of those have a decent GUI to go with them? –  Hugh Allen Sep 27 '10 at 14:03
    
Edited do answer your question.... but I would say : "No, they dont", but I hear abiword supports OCRopus (arstechnica.com/open-source/news/2007/08/…) –  Krazy_Kaos Oct 13 '10 at 11:32
    
+1 for adding screenshots to answer and also for mini-reviewing the two offered programs... –  Kurt Pfeifle Jun 18 '11 at 19:38

There is also TOPOCR (a.k.a SnapReader), containing post-processing Spell Checker for 11 Languages:

SnapReader can be used to make your own searchable notes from almost any document image. Or you can use it as an an authoring tool and create your own editable content using your scanner or camera and save the results as HTML or PDF. SnapReader can also transform text into very high quality audio using Audrey. So not only can you use your scanner or camera to capture documents, you can now also use your portable music player or smartphone to "read" them.

image

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.