Abstract
This paper presents a shared-memory parallel algorithm for computing connected
pattern spectra from the Max-Tree structure. The pattern
spectrum is an aggregated feature space derived directly from the
tree-based image representation and is a powerful tool for
interactive image information mining. An application example along
with timings on experiments with Gpixel input imagery are given. On
images of 0.87 to 1.29 Gpixel, wall-clock times of 8.13 to 15.17s, and
a speed up of between 27.5 and 33.5 were achieved on a single 2U
64 core rack server.
pattern spectra from the Max-Tree structure. The pattern
spectrum is an aggregated feature space derived directly from the
tree-based image representation and is a powerful tool for
interactive image information mining. An application example along
with timings on experiments with Gpixel input imagery are given. On
images of 0.87 to 1.29 Gpixel, wall-clock times of 8.13 to 15.17s, and
a speed up of between 27.5 and 33.5 were achieved on a single 2U
64 core rack server.
| Original language | English |
|---|---|
| Title of host publication | ESA-EUSC-JRC 8th Conference on Image Information Mining |
| Pages | 21-25 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - 2012 |
| Event | ESA-EUSC-JRC 8th Conference on Image Information Mining - German Aerospace Centre (DLR) , Oberpfaffenhofen, Germany Duration: 24-Oct-2012 → 26-Oct-2012 |
Conference
| Conference | ESA-EUSC-JRC 8th Conference on Image Information Mining |
|---|---|
| Country/Territory | Germany |
| City | Oberpfaffenhofen |
| Period | 24/10/2012 → 26/10/2012 |