To even don't let come up the feeling that we might have nothing to present here, I'll blog a bit between work, university and (later that evening) homework.
A new semester began early in April; and as the passed one, it is accompanied by a new, really interesting project for me :) But let me explain.
Maybe you already have heard of a neat little toy called digital pen&paper. If not: The idea is, that you have a pen. And you write with it. Yes, ordinary writing on a sheet of paper. However, somewhere the "digital" must come in ;) The pen sends information to a device, that you can attach to your computer. This device then records the things you've written on the paper and saves them (you might think of that as if working with a pen in tools like GIMP). The saved strokes can than either be saved as an image (so you get a "scanned" version of your handwritten stuff, though without scanning) or as a "strokes" page (i.e. the lines you drew are saved in a fitting format). Cool, isn't it? You can even set up that stuff to work as HID device (you can then use it similar to a graphic tablet). This way, you can use handwriting recognition software to directly digitalize your writing.
Now, if you think of it: Does this really make sense? For someone like me - a student - probably not. If I want a version of my handwritten stuff I can scan it. If I need it digitalized I take my netbook with me and write stuff there. But there are indeed cases, where such a setup makes sense! Currently, often things are still written on paper; for example in a hospital (where the doc has to fill forms about you) or on a mess (for example a contact form). This is due to human nature (and habits, of course). But actually, these information are needed digitalized (e.g. the data from the doctor's form might be needed by others in the hospital, so having it available in the local network is essential; similarly, the contact data from the mess is actually further processed and stored on computers anyway). So, after taking the notes using (analog) pen&paper in a second step the forms must be digitalized by hand; a time consuming and boring job (unless the persons have a really bad handwriting, so that "decoding" their writings is kinda game).
Here comes the digital pen&paper idea in: Using such a device, the conversion step can be omitted. The data - even though written in a known way - is simultaneously available digitalized and can easily be transferred into the local network and thus is accessible nearly immediately. Well... at least it could be.
Consider a form as the doctor fills it out. There, we have several problems:
Even if we have the strokes data from the pen, we don't know exactly which page (assuming a form with several pages) a digital page belongs to. We can make assumptions ("the doc will always fill the forms out in the same order"), but as you know, a lot of assumptions tend to don't hold when it comes down to the point where you need them. This means for us: We need to find out, which digitalized page belongs to which page of the form.
This would maybe even be easy, but we have another problem: What, if the receiver device is badly positioned and thus the recorded strokes are transformed compared to how the form actually looks like (e.g. moved a bit to the left/bottom, rotated by some degrees and so forth). This makes a mapping of strokes to pages of the form even more difficult; especially, as there is a cyclic dependency: To know, which page of strokes belongs to which page of the form we would need the strokes positions correctly inside their page. On the other side, to get the correct transformation, we need to know which page of the form to target.
This cyclic dependency can be broken up a bit: By scanning the pages of the form afterwards and evaluating the scanned images, it is possible to map the stroke pages to the pages of the form. This decreases the comfort factor a bit of course (the sense of digital pen&paper is to avoid an additional step), however, we assume that scanners scan faster than humans are able to type in the information by hand (and especially with progress in techniques this assumption is likely to hold).
Now, then, AI comes in. Our (yep, this time it's a two-man-project ;) ) task is, to use algorithms and ideas from AI, to extract the information, make the mapping and thus ease digitalizing handwritten forms even further. I think, this will be really fun; especially, as we were asked to realize the project using C#/.NET. So... hey Mono, so we meet again :)
=-=-=-=-=
Powered by Blogilo