I just caught myself thinking: "I hope they got a software patent on this, they deserve it." But I usually hate software patents unequivocally. So, yet again, a real-world use case reminds me that nothing is so black and white.
The problem is that it is a clever combination of techniques that already exist.
* OCR, to identify the text
* Removing the background of the text, filling it with surrounding colors
* Translating words
* Placing new words on the same area, using the same rectangle
It's very, very clever, but it's not something that should be controlled by one person or company. Should any combination of existing techniques will also be patentable? Where do we draw the line?
They were the first and they'll have a head start and make a lot of money. Now, be exclusive? I don't think so.
As a friend who knows octavio, they've tried various "OCR" techniques from typical journal papers and in general those types of algorithms were mostly for static images. They struggled for 2 years to find the best techniques and I think they final product is great.
As a programmer, sometimes I think "this could be patentable, because the implementation is not immediately obvious to me." Maybe the non-programmers at the USPTO apply the same standard.
The problem with this reasoning is obvious: given that "idea patents" are now commonly awarded, these guys are much more likely to be sued by a troll who has already acquired a patent on the idea, than they are to be able to defend their IP by threatening a patent suit against someone else. An eye for an eye leaves the whole world blind.
Patents are no defense against patent trolls, because (by definition) the patent trolls don't actually produce anything. There is no defense against patent trolls, except lobbying to narrow the scope and duration of technology patents.
