Remember this Photoshop CS5 sneak peak showing off it’s latest and greatest feature Content-Aware Fill a couple months ago, well it turns out a reasonably old plug-in for GIMP (GNU Image Manipulation Program) named Resynthesizer seems to work just as great and because it is what it is, it’s free and open-source.

Installing on Ubuntu 9.10/10.04 install:

or for the Source/Windows/Fedora Core 4 versions see the download section.

Once you have it installed, it’s simple to use really just select something on your image that shouldn’t be there and right click on the selection Filters -> Map -> Resynthesize.. and up should pop an options box, these settings are pretty standard and will get rid of most things given that they aren’t too big. It’s best if you’re not getting the results you want to play around with the settings yourself to get to know them better.

Click after the break for an example with step by step guide.

Example:

Let’s see, we start out with this nice photo of a house but wait.. what are those smelly students doing there? Well, let’s sort that out..

First thing you’ll want to do is grab your best selection tool and cut around the edge of those waste of time students..

Now all you have to do is right click Filters -> Map -> Resynthesize..

Next here, you can just hit the Ok button and watch as they magically disappear (probably back to their germ infested student flat).

Now you can just do that for anything, however while doing the edges some strange things happen with the default settings:

To counteract this, I found unchecking “Make vertically tileable” seemed to fix this and I would assume (without trying) that if you are doing a vertical edge you might want to take off the horizontally tileable option.

This brings the end result to a pretty reasonable (student free) image only after a couple of minutes, much better than could be expected from using the clone tool and whatever other means you would go through.

Install:

(Ubuntu 9.10)

sudo apt-get install tesseract-ocr tesseract-ocr-eng

Preparing Images for Tesseract with GIMP:

1. Load an image with text into GIMP
2. Image > Mode > make the image RGB or Grayscale.
3. Tools > Color Tools > Threshold > pick a value which best shows the text
4. Image > Mode > Indexed > choose 1-bit & no dithering.
5. Save the image as .tif (TIFF but make sure the extension is only .tif and not .tiff)

Use:

The input file MUST be .tif (not .tiff) and the output will be a .txt (extension is automatically added by tesseract) so simply typing the following should export the input image (input.tif) as a text file (output.txt).

tesseract input.tif output

Example:

Example Output:
Hello World
Alex Sleat
Testing test
All this information was found on the following Ubuntu documentation, I just had some trouble finding it so I have re-wrote as a clean simple guide for anyone else having the same trouble. All thanks goes to whoever wrote the following link. :)

https://help.ubuntu.com/community/OCR