Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A hybrid supervised-unsupervised vocabulary generation algorithm for visual concept recognition

: Binder, A.; Wojcikiewicz, W.; Müller, C.; Kawanabe, M.


Kimmel, R.; Klette, R.; Sugimoto, A.:
Computer vision - ACCV 2010 : 10th Asian Conference on Computer Vision, Queenstown, New Zealand, November 8 - 12, 2010. Revised selected papers. Part III
Berlin: Springer, 2011 (Lecture Notes in Computer Science 6494)
ISBN: 978-3-642-19318-7
ISBN: 978-3-642-19317-0 (print)
ISSN: 0302-9743
Asian Conference on Computer Vision (ACCV) <10, 2010, Queenstown>
Conference Paper
Fraunhofer FIRST ()

Vocabulary generation is the essential step in the bag-of-words image representation for visual concept recognition, because its quality affects classification performance substantially. In this paper, we propose a hybrid method for visual word generation which combines unsupervised density-based clustering with the discriminative power of fast support vector machines. We aim at three goals: breaking the vocabulary generation algorithm up into two sections, with one highly parallelizable part, reducing computation times for bag of words features and keeping concept recognition performance at levels comparable to vanilla k-means clustering. On the two recent data sets Pascal VOC2009 and Image-CLEF2010 PhotoAnnotation, our proposed method either outperforms various baseline algorithms for visual word generation with almost same computation time or reduces training/test time with on par classification performance.