How to read blacked-out gov documents

I found a cool aritcle on The Register about how to circumvent the typical US government practice of marking through sensitive parts of documents so that it can't be read.

From the article:

An Irish graduate student has uncovered words blacked-out of declassified US military documents using nothing more than a dictionary and text analysis software.

The first task is to identify the font, and font size the missing word was written in. Once that is done, the dictionary search begins for words that fit the space, plus or minus three pixels.

Although the technique is no good for tackling larger sections of text, it does show that officials need to be more careful with their sensitive documents.

I just wish the article gave more detail as to the software used in this process. There are quite a few MJ12 documents that I'd like to see "decoded" in this fashion.

I personally despise the black out lines. I am familiar with this method and have tried it on my own a few times. It works, but only in a very limited fashion. That and it's more like playing mad libs with those declassified documents. I remember some funny results I came up with was along the lines of:

"shoot lark rail green" and "top official compact agreement silly"

but it's totally hypocritical to declassify a document, and then go on to hide stuff by blacking out the most important parts with a sharpie. Another reason to disbelieve the existence of democracy in the United States; a government that incessantly hides itself is not only being dishonest, it lacks transparency

Originally posted by AlnilamOmega
I am familiar with this method and have tried it on my own a few times. It works, but only in a very limited fashion.

What text analysis software did you use? I would be interested in trying this out for myself.

but it's totally hypocritical to declassify a document, and then go on to hide stuff by blacking out the most important parts with a sharpie. Another reason to disbelieve the existence of democracy in the United States; a government that incessantly hides itself is not only being dishonest, it lacks transparency

I couldn't agree more.

It was an OCR (optical character recognition) enabled piece of software I used at one of my former jobs to process forms. I found this plugin on the net that would read through blacked-out lines called "WYSIWYGhack" or something like that, but I just tried to look for it now and was unable to find it so my memory could be a bit off on the name. I am sorry I couldn't be very helpful on this matter.

Originally posted by AlnilamOmega
It was an OCR (optical character recognition) enabled piece of software I used at one of my former jobs to process forms. I found this plugin on the net that would read through blacked-out lines called "WYSIWYGhack" or something like that, but I just tried to look for it now and was unable to find it so my memory could be a bit off on the name. I am sorry I couldn't be very helpful on this matter.

Thanks for the info. I'll start looking around for some add-ons to OmniPage Pro.