Abstract
We present a new method for morphological connected attribute filtering for object
detection in astronomical images. In this approach, a threshold is set on one attribute
(power), based on its distribution due to noise, as a function of object area. The results
show an order of magnitude higher sensitivity than a state-of-the-art method.
detection in astronomical images. In this approach, a threshold is set on one attribute
(power), based on its distribution due to noise, as a function of object area. The results
show an order of magnitude higher sensitivity than a state-of-the-art method.
| Original language | English |
|---|---|
| Title of host publication | 11th International Conference "Pattern Recognition and Image Analysis |
| Subtitle of host publication | New Information Technologies" (PRIA-11-2013) |
| Pages | 746-749 |
| Number of pages | 4 |
| Publication status | Published - 2013 |