Handwriting recognition

Happy new year to you all.

I was very hardworking within the two weeks of holiday. Ok that’s not true, I only let others work for me :)   Ten people wrote eachone 10 to 15 notes and a text consisting of five paragraphs. So the minimum of writers are handled. I will try to find another five people, then there is enough data to evaluate.

To get some ideas for the graphical user interface of the iLiad application I talked to my supervisor. We did some brainstorming and here is the result:

There are two areas. One analog area wherein the user writes his text and a digital area where the result will be shown.

In the digital area you can see the following:

1. The recognized text. In difference to the first two UI suggestions there is a novel functionality. Not only the best, but the first two (or maybe more) alternatives for each word are shown. So the user needs less interaction to choose the right one. If the alternatives are still wrong the user can click on the three dots and a list with further alternatives will appear.
2. Above each alternative iDocument found information about, there are the icons that were introduced in the first UI example. The difference is, that the user chooses the right one by clicking on it. Only if he wants to see further information about the instance, he needs to click on the little triangle and the known popup window appears.
3. On the right side of the digital area there are the action buttons. The actions were introduced in a former post. Nothing changed.

I think this is a very good solution for an intuitive user interface. And beside that there are as less interactions as possible. I hope this all works with the GTK+ (http://www.gtk.org/) framework…

Today I prepared data for the evaluation of my webservice. I took some texts from http://www.bbc.co.uk/music and extracted rdf data of this service as well as from dbpedia (http://dbpedia.org/).

In the next two weeks I want to let 15 persons write five texts each and addidionally some notes. To evaluate the results will be very interesting to me. I’m really excited, how the results will look like and how I can (hopefully) improve them by changing the algorithm inside my webservice.

When I had a call to my supervisor the last time, we talked about  a publication again. He told me that there is a conference for handwriting recognition (see http://www.isical.ac.in/~icfhr2010/index.html). If I had first results of my evaluation I could write a paper and submit it there. That would be really great.  Especially because this is a specialized conference. Deadline for submitting is February, 15th. So I have to hurry up, to get this done. Of course that means a lot more work to be done, but it could help me in future.

A long time passed since I wrote the last entry. Sorry for that, but there were some really big problems I ran into. In the last three weeks I tried to compile some C++ source and some libraries for the ebook reader iLiad. Normally this wouldn’t be a problem, but that device uses an ARM CPU. Thus I can’t simply compile my code. No. Instead I need to cross compile anything. That means I need to compile code for an architecture that is different to the one I use.

First I tried to compile it with arm-linux-gcc, this didn’t work at all. Afterwards I used scratchbox (http://www.scratchbox.org/) and an inofficial toolchain for the iLiad. And finally, in the last week, it worked. Tanks to an advisor of mine who helped me a lot (you know who I mean :)

I am so happy that it works now. But although, it took three weeks that are now lost. Anyway. I can now proceed in caring about problems regarding my diploma thesis.

I never wrote about what will happen with the text, the user chooses to be recognized right.

There are three possible actions the user can perform:

1. save the information
2. discard the information
3. use the text as a new container name (see below)

The webservice saves some kind of container. This is called a “research box” (or short rebo :), because it will contain any information that Robert (the journalist) wants to save for one research topic.

If he writes something onto the iLiad and sends this text to the webservice, he will get back information about the text. Then he chooses the right text and the semantic information he wants to save for later use. These are sent back to the webservice. Now this one can save everything in the research box. Therefore it uses a rdf format called TriG (see: http://www4.wiwiss.fu-berlin.de/bizer/TriG/). TriG is a compact format that contains so called named graphs (http://www.w3.org/2004/03/trix/). Every note Robert chooses for inserting into the research box will be a new graph.

As mentioned above the research box has a topic it belongs to. So it needs a name that differs for every topic. This name is the “reboname”. The user can choose a written text to be the name of the rebo. If it already exists, new data will be appended to it, otherwise a new empty container will be created.