Refine
Year of publication
Document Type
- Article (31421) (remove)
Language
- English (16026)
- German (13387)
- Portuguese (696)
- French (387)
- Croatian (251)
- Spanish (250)
- Italian (134)
- Turkish (113)
- Multiple languages (36)
- Latin (35)
Has Fulltext
- yes (31421)
Keywords
- Deutsch (503)
- taxonomy (451)
- Literatur (299)
- new species (194)
- Hofmannsthal, Hugo von (185)
- Rezeption (178)
- Übersetzung (163)
- Filmmusik (155)
- Johann Wolfgang von Goethe (131)
- Vormärz (117)
Institute
- Medizin (5408)
- Physik (1958)
- Biowissenschaften (1152)
- Biochemie und Chemie (1113)
- Extern (1108)
- Gesellschaftswissenschaften (803)
- Frankfurt Institute for Advanced Studies (FIAS) (753)
- Geowissenschaften (593)
- Präsidium (453)
- Philosophie (448)
We present a biologically-inspired system for real-time, feed-forward object recognition in cluttered scenes. Our system utilizes a vocabulary of very sparse features that are shared between and within different object models. To detect objects in a novel scene, these features are located in the image, and each detected feature votes for all objects that are consistent with its presence. Due to the sharing of features between object models our approach is more scalable to large object databases than traditional methods. To demonstrate the utility of this approach, we train our system to recognize any of 50 objects in everyday cluttered scenes with substantial occlusion. Without further optimization we also demonstrate near-perfect recognition on a standard 3-D recognition problem. Our system has an interpretation as a sparsely connected feed-forward neural network, making it a viable model for fast, feed-forward object recognition in the primate visual system.
In November 2005, a survey was begun of the wells in and around Hagia Sophia Church in Istanbul. The long-term goal of the survey is the understanding of the function of the tunnels and the water systems used for Hagia Sophia and its surroundings during the Byzantine and the Ottoman periods. Alternate research methods, such as geophysical research, will be used in future surveys. The 2005 survey examined the channels that run from under the narthex and continue northwards and the southwards of the building as well as channels that run towards the atrium, hippodrome, and garden in the north. The survey resulted in the first photos of the well-bottoms in the history of Hagia Sophia.