Selected Readings in Vision and Graphics
edited by Luc Van Gool, Gábor Székely, Markus Gross, Bernt Schiele

Volume 53

 

 

 

Till Quack

 

Large-Scale Mining and Retrieval of

Visual Data in a Multimodal Context

 

2009. XVIII, 226 pages. EUR 64,00.

ISBN 978-3-86628-253-7

 

This book discusses recent research results in the fields of object mining and object retrieval in visual data. The three main field covered are: Firstly, the investigation of itemset mining algorithms in the domain of visual data for recognition of specific objects and object classes.

The second topic is a multi-modal data-mining method, which automatically mines objects and events from community photo collections on the Internet. This is achieved trough a combination of multi-modal cues, stemming from image-data, text-data and geographic location.

The third and final topic consist of several prototype applications for scalable retrieval in visual data, partly building on the data mined in the previous steps. These retrieval applications focus on applications for mobile devices, including multimodal context such as GPS location of the user. In addition to the mobile retrieval applications, novel web-and desktop applications are designed, for browsing and auto-annotation in personal photo collections.

About hte Author

Till Quack obtained a M.Sc. degree in Information Technology and Electrical Engineering from ETH Zurich in 2004. From 2004 to 2009, he was research assistant and Ph.D. student at the Computer Vision Group of the Swiss Federal Institute of Technology (ETH), Zurich, Switzerland, with Prof. Luc Van Gool. He received his Ph.D. in Computer Science (Dr.sc.techn.) from ETH Zurich for his work on mining and retrieval of visual data in a multimodal context in 2009. He is also co-founder of several startup companies in the Internet and Computer Vision industries.

Keywords / Schlagwörter:
object recognition, object retrieval, image retrieval, computer vision, machine learning, internet vision, data mining, Objekterkennung, Bildverstehen, maschinelles Lernen, Bildsuche

 

Reihe " Selected Readings in Vision and Graphics " im Hartung-Gorre Verlag

Direkt bestellen bei / to order directly from:


Hartung-Gorre Verlag / D-78465 Konstanz / Germany

Telefon: +49 (0) 7533 97227 Telefax: +49 (0) 7533 97228

http://www.hartung-gorre.de
eMail: verlag@hartung-gorre.de