Avtor/Urednik		Dai, Mo
Naslov		An edge preservating iterative filtering for image processing
Tip		članek
Vir		Image Anal Stereol
Vol. in št.		Letnik 20, št. Suppl 1
Leto izdaje		2001
Obseg		str. 245-50
Jezik		eng
Abstrakt		Based upon edge detection, an iterative filter is proposed in this paper. It is capable of smoothing noise either additive or multiplicative while preserving discontinuities in the image. This is achieved by repeatedly convolving the image with a very small averaging mask weighted by 0 or 1. The criterion to measure the continuity in the image at each iteration is submitted the Gaussian distribution. The last property allows us to stop iteration automatically. If it is necessary, a postfiltering (stack corona filtering) can be performed to improve the result. The application of this filter ranges from geology, medical images processing to radar image restoration.
Deskriptorji		PARTICLE SIZE NORMAL DISTRIBUTION IMAGE PROCESSING, COMPUTER-ASSISTED