Paper Info
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 Friedlander100.34
Marcus Frean215716.60
Melanie Johnston-Hollitt300.68
Christopher Hollitt4448.91