Today I created a presentation on Caliph and Emir and I looked up how long these open source projects are now part of my (online & research) life. In July 2004 I put the first open source version of Caliph & Emir online and ~ 6.700 downloads happened from then till now. Furthermore the Java Web Start files of Caliph and Emir were accessed about 1.300 times. Lire was more successful: Going online in 2006 it was ~3.600 times download till now.
Taking a look around I have to say that Caliph is still the only MPEG-7 tool for semantic descriptions. Due to the fact that it is a prototype (with virtually no productive use) i assume that there is currently no need for such a tool. Reported use is focused on MPEG-7 development and research projects. Lire on the other hand has a more active user base: I know several projects where Lire is used. Seems like there actually is a need for an open source Java library for content based image retrieval.
Since Blobworld was down I was hoping for a new online CBIR system to show in lectures. Last week I received word about the img(Anaktisi) image search engine from Savvas Chatzichristofis. This search engine is based on 2 new content based descriptors that combine color and edge features. The results look promising!
There is also an offline sketch based retrieval system being developed. A screencast can be found on YouTube.
You might all know del.icio.us, the social bookmarking service. As I use this a lot and also did some research in this direction recently (see e.g. here) I wanted to try out more Within my preparations for the Multimedia Information Systems course this semester I checked in how far LSA (latent semantic analysis) can be applied to tags and made also a small demo application. The demo fetches the RSS feed from a given user name (leave the name field blank for random names, separate multiple names by commas) and computes a co-occurrence matrix after a latent semantic analysis. Note that only the last ~30 entries are in the feed. You might then select a tag from the combo box and find the related ones.
The tool can be accessed via Java Web Start here. Drop me a line whether you like it or not.
From the web page: The TRIPLE-I Conference series is a joint venture of the conferences I-KNOW, I-MEDIA and I-SEMANTICS. TRIPLE-I reflects the increasing importance and convergence of knowledge management, new media technologies and semantic systems. This unique concept aims at bridging the gaps between the various communities and their technology fields.
Last years TRIPLE-I was a great success, so I’m looking forward to this event. It’s scheduled 3-5 September in Graz. Austria. Full paper submission deadline is April, 14th.
My former employer has several interesting job offers posted here and here. They are searching for people who have finished their master studies recently. The work focuses either on knowledge discovery (information retrieval, data mining, etc.) or knowledge services (workplace learning and so on).
Some time ago I realized that there is obviously a market for educational games for (very young) kids. I made my first small game SoundMachine some year and a half ago and a second one around last Christmas. I now finished to polish the two games and package them into a single archive. I also changed them to Java 1.6 and made some help. There is also some i18n for English and German. Today I release them as open source games.
GuessWhat: This game displays images (randomly or in sequence) hidden by 6 blocks. With each mouse click (e.g. by touch screen) or pressed key one block vanishes and a part of the image appears. The image sets are configurable. Adding your own image set is easy: Just copy them to a subfolder in the unzipped folder.
Soundmachine: This game features a blue ellipse dangling around on a black screen. Pressing a button increases the twist of the ellipse and results in a rapid change of the background (like a flash).
Download the games along with the source and unzip them. Windows users will find executable files to start the games. Note that Java 1.6 has to be installed. Linux users will be able to run the games using the commands given in the batch files.
Being the proud owner of a GPS Logger I though a bit about developing a Java applications for geotagging photos and analyzing my tracks (e.g. for running, biking and hiking). While this is all possible with online applications (e.g. barrique) I searched a lot for free offline tools. I did find some applications, which provide sufficient functionality (e.g. GeoSetter, which works really fine) but only work on Windows
Unfortunately I currently have not enough time sit down and code a fine app, but I did some search and found out that it might be rather easy to mash up such tool. First thing is parsing of GPS data -> That’s just XML (with GPX) and should be rather easy. Reading time from the photos EXIF tags can be done with Drew Noakes library. It also allows reading of the EXIF thumbnails for boosting “time to display”. The visualization can be done with the Swing-X WS JXMapViewer component (hopefully). Writing the geo tags using EXIF might be done with Imagero (Java, a bit on the expensive side) or ExifTool (Perl, open source). I’d appreciate feedback on possible other libs
After some requests I started a document on the Lire internals (how this approach actually works). In a first shot I described how descriptors are stored within Lucene and how the retrieval is done. If you read those few words feel free to add information and eliminate typos etc. – it’s a wiki
Last Monday the post proceedings of the Common Sense and Goal Oriented Interfaces Workshop (CSKGOI 08) in January in Gran Canaria went online. We chose the Ceur Workshop Proceedings server for post publication. It’s an open access server with a rather easy submission procedure and papers normally get indexed by Google Scholar and Citeseer. All papers are available along with a nice short preface as Vol. 323: