====== Image and Video Analysis ======

Here is the full list of MADM image and video analysis demos, containing web demos as well as off-line ones.
 
 
 
===== Web Demos ===== 

 ==== TubeTagger ====
<columns - 220 - >
[[http://madm.dfki.de/demo/tubetagger|{{:tube_tagger_screen_200.png?200}}]]
<newcolumn>
TubeTagger is a concept-based video retrieval system that learns to detect visual concepts (like "soccer", "desert", or "interview") automatically from YouTube. The demo allows you to search a video collection using keywords. The videos have been indexed completely automatically by TubeTagger - no manual tagging was done!

[[http://madm.dfki.de/demo/tubetagger|link to demo]]
[[http://www.dfki.uni-kl.de/~ulges/tubetagger-page|description]]
[[http://www.dfki.uni-kl.de/~ulges/moonvid|MOONVID project]]
[[adrian.ulges@dfki.de|contact]]
</columns>

\\

===== Smart Video Buddy =====
<columns - 220 - >
[[http://madm.dfki.de/demo/smartvideobuddy|{{:livetagger-screenshot-small.png?200|}}]]
<newcolumn>
Smart Video Buddy is an intelligent assistant that understands videos and links them with other content. Semantic concepts (like "soccer game") are detected in real-time, and this information is used to "make videos smarter", i.e. to enrich them with adapted news, advertisements, or interesting links. Smart Video Buddy was presented at the CeBIT 2010.

[[http://madm.dfki.de/demo/smartvideobuddy|link to demo]]
{{:tagging-flyer.pdf|demo flyer}}
[[/moonvid|MOONVID project]]
[[adrian.ulges@dfki.de|contact]]
</columns>

\\

 ==== InViRe - Intelligent Video Retrieval ====
<columns - 220 - >
[[http://madm.dfki.de/demo/invire|{{:invire_screen_200.png?200}}]]
<newcolumn>
The InViRe system realizes content-based retrieval in a dataset of TV content. If you click on a scene, InViRe uses video fingerprints based on a video's color, texture, and motion to retrieve similar scenes.

[[http://madm.dfki.de/demo/invire|link to demo]]
[[http://www.dfki.uni-kl.de/~ulges/invire-page|description]]
[[christian.schulze@dfki.de|contact]]
</columns>

\\

 ==== TubeFiler ====
<columns - 220 - >
[[http://madm.dfki.de/demo/tubefiler|{{:tubefiler_screen_200.png?200}}]]
<newcolumn>
TubeFiler is an automatic genre categorizer for YouTube videos. Given a tagged YouTube clip, the system automatically sorts it into a hierarchy of genres (such as "travel->skiing") and performs a refinement of categories based on a visual clustering.
We participated with TubeFiler in the [[http://comminfo.rutgers.edu/conferences/mmchallenge/|ACM Multimedia Google Grand Challenge 2009]].

[[http://madm.dfki.de/demo/tubefiler|link to demo]]
[[http://www.dfki.uni-kl.de/~ulges/tubefiler-page|description]]
[[http://www.dfki.uni-kl.de/~ulges/moonvid|MOONVID project]]
[[adrian.ulges@dfki.de|contact]]
</columns>

\\

 ==== Pornography Detection ====
<columns - 220 - >
[[http://madm.dfki.de/demo/fives|{{:fivesdemo.png?200}}]]
<newcolumn>
This demo illustrates the automatic recognition of pornographic material using computer vision techniques (with a click, you can re-rank material in a database such that potentially offensive content is shown). We developed the system as part of the [[http://fives.kau.se|FIVES]] project, in which we develop a toolbox supporting police investigators with the detection of illegal child pornographic material.

[[http://madm.dfki.de/demo/fives|link to demo]]
[[http://fives.kau.se|FIVES project]]
[[adrian.ulges@dfki.de|contact]]
</columns>

===== Other Demos ===== 

 ==== Navidgator - Image Browsing using Clustering ====
<columns - 220 - >
[[http://madm.dfki.de/demo/fives|{{:navidgator_screen_200.png?200}}]]
<newcolumn>
The Navigator online demo allows a structural browsing of image/video databases based on visual appearance. You can define images as your current focus of interest, and zoom into the image collection or pan over it just like you do it with a map. The system provides a web demo for browsing collections of images and video frames.

[[http://madm.dfki.de/servlet/navidgator-tv|link to TV demo]]
[[http://madm.dfki.de/servlet/navidgator|link to image demo]]
[[http://madm.dfki.de/navidgator|description]]
[[adrian.ulges@dfki.de|contact]]
</columns>


 ==== GRIML - Graphics and Image Labeling ====

<columns - 220 - >
[[http://madm.dfki.de/demo/griml|{{:demos:griml.png?200}}]]
<newcolumn>

GRIML is a general-purpose tool for auto-annotating your pictures, which - in contrast to most other image annotation software - cannot only handle photos but also other content like graphics and icons. To do so, GRIML performs a hierarchical classification of pictures: first a coarse classification into general categories is performed, followed by a fine-grain tagging.

[[http://madm.dfki.de/demo/griml|link to demo]]
[[adrian.ulges@dfki.de|contact]]
</columns>