Title | ||
---|---|---|
Latent Dirichlet allocation for image segmentation and source finding in radio astronomy images |
Abstract | ||
---|---|---|
We present exploratory work into the application of the topic modelling algorithm latent Dirichlet allocation (LDA) to image segmentation in greyscale images, and in particular, source detection in radio astronomy images. LDA performed similarly to the standard source-detection software on a representative sample of radio astronomy images. Our use of LDA underperforms on fainter and diffuse sources, but yields superior results on a representative image polluted with artefacts --- the type of image in which the standard source-detection software requires manual intervention by an astronomer for adequate results. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2425836.2425918 | IVCNZ |
Keywords | Field | DocType |
radio astronomy image,diffuse source,image segmentation,latent dirichlet allocation,adequate result,source finding,standard source-detection software,exploratory work,greyscale image,algorithm latent dirichlet allocation,representative sample,representative image,radio astronomy | Radio astronomy,Astronomer,Computer vision,Latent Dirichlet allocation,Pattern recognition,Computer science,Image segmentation,Software,Sampling (statistics),Artificial intelligence,Topic model,Grayscale | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anna Friedlander | 1 | 0 | 0.34 |
Marcus Frean | 2 | 157 | 16.60 |
Melanie Johnston-Hollitt | 3 | 0 | 0.68 |
Christopher Hollitt | 4 | 44 | 8.91 |