Visual Computing - Research Demos
at HTW Berlin
Our main research interests are Information Retrieval, Machine Learning, Visualization, Computer Vision, and visual clustering & sorting
Prof. Dr.-Ing. Kai Uwe Barthel (barthel at htw-berlin.de)
Prof. Dr. Klaus Jung (klaus.jung at htw-berlin.de)
M.Sc. Nico Hezel (hezel at htw-berlin.de)
akiwi is a semi-automatic image tagging system able to suggest keywords for unknown images with minimal user input. Use akiwi to find keywords for your images. www.akiwi.eu
We won the Video Browser Showdown 2016, where the participating teams had to perform several interactive video search tasks in 250 hours of video content. www.videobrowsershowdown.org/winners
Use picsbuffet to visually browse millions of images in your browser. As with mapping systems you can easily explore and search huge sets of images. www.picsbuffet.com
In this demo we have applied the picsbuffet idea to visually browse IKEA product images. Please use German keywords for searching products. picsbuffet.com/ikea
Clustering helps to get an overview of different concepts associated with a query. Even with very vague keywords particular images can be found very quickly. palm.visual-computing.com
Image navigation the better way. Due to the visual sorting, PicsLikeThat can show several hundred images allowing easy inspection. www.picslikethat.com
The game Apetopia helps the computer to determine perceived color differences. Players choices are used to model better color metrics. apetopia.visual-computing.com