Zoomable Cell
Zusammenfassung der Projektergebnisse
The Zoomable Cell project advanced the scientific knowledge in several important aeas. During its course it also faced surprising setbacks. Foremost one must name the data issue, i.e. the access to labelled images of cell content at the desired resolution interval. We turned this problem into an asset by focussing our research on image retrieval and classification problems. We successfully developed and published • a novel model for an apparent phenomenon of the visual world the surrounds us that can lead to new insights in the system visual system and can be used as image descriptor, • two novel browsing methods that facilitates retrieving images with specific semantic content, • an algorithm that was verified to usefully propagate information along a neighbourhood of images that was established by visual similarity, and finally • a method and its implementation to optimize the individual components the constitute the semantic image retrieval pipeline. Naturally, goals set in the original proposal were met as well. These include • a semi-automatic morphing technique that can be used to blend between images depicting non-rigidly transformed versions of the same physically object, • the determination of the structure of the histone methyltransferase complex set1c from saccharomyces cerevisiae using constraint-based docking, and • a semi-automated ontology generator from unstructured texts.
Projektbezogene Publikationen (Auswahl)
- Semi-automated ontology generation within oboedit. Bioinformatics, 26(12):i88-i96, 2010
Thomas Wächter and Michael Schroeder
(Siehe online unter https://doi.org/10.1093/bioinformatics/btq188) - Structural modeling of histone methyltransferase complex set1c from saccharomyces cerevisiae using constraint-based docking. Proteomics, 10(23):4186-4195, 2010
Anne Tuukkanen, Bingding Huang, Andreas Henschel, Francis Stewart, and Michael Schroeder
(Siehe online unter https://doi.org/10.1002/pmic.201000283) - Visuelle Analytik biologischer Daten. Informatik-Spektrum, 33{6):559-568, 2010
Kay Nieselt, Michael Kaufmann, Andreas Gerasch, Hans-Peter Lenhof, Marcel Spehr, Stefan Hesse, and Stefan Gumhold
(Siehe online unter https://doi.org/10.1007/s00287-010-0482-y) - Directed image search with local parallel feature axes. In 2011 IEEE International Conference on Multimedia and Expo, pages 1-6. IEEE, 2011
Stefan Gumhold and Marcel Spehr
(Siehe online unter https://doi.org/10.1109/ICME.2011.6012228) - Sum-of-Superellipses—A Low Parameter Model for Amplitude Spectra of Natural Images. In Proceedings of the 16th International Conference on Image Analysis and Processing (ICIAP): Part I, pages 128-138. Springer-Verlag, 2011
Marcel Spehr, Stefan Gumhold, and Roland W. Fleming
(Siehe online unter https://doi.org/10.1007/978-3-642-24085-0_14) - Network compression as a quality measure for protein interaction networks. PLoS One, 2012
Loic Royer, Matthias Reimann, Francis Stewart, and Michael Schroeder
(Siehe online unter https://doi.org/10.1371/journal.pone.0035729) - Efficient Browsing in Image Databases Using a Hierarchy of Kernel PCA Subspaces. In Proceedings of lADIS Computer Graphics, Visualization, Computer Vision and Image Processing 2013 (CGVCVIP 2013), pages 99-110, 2013
Marcel Spehr, Frank Herrlich, Stefan Hesse, and Stefan Gumhold
- Feature Propagation on Image Webs for Enhanced Image Retrieval. In Proceedings of the 3rd ACM International Conference on Multimedia Retrieval - ICMR '13, pages 25-32, New York, New York, USA, April 2013. ACM Press
Eric Brachmann, Marcel Spehr, and Stefan Gumhold
(Siehe online unter https://doi.org/10.1145/2461466.2461472) - Wifbs: A Web-based Image Feature Benchmark System. In Proceedings of 21st International Conference on MultiMedia Modelling, 2015, Sydney, Australia, January 5-7, 2015, pages (159-170), 2015
Marcel Spehr, Sebastian Grottel, and Stefan Gumhold
(Siehe online unter https://doi.org/10.1007/978-3-319-14442-9_14)
