Author/Editor		Tomaževič, Dejan; Likar, Boštjan; Pernuš, Franjo
Title		Retrospective shading correction: problem, methods, and evaluation
Type		članek
Source		In: Svoboda T, editor. Proceedings of the Czech pattern recognition workshop 2000; 2000 Feb 2-4; Peršlak, Czech Republic. Praha: Czech pattern recognition society,
Publication year		2000
Volume		str. 15-20
Language		eng
Abstract		In this paper we address the problern of retrospective shading correction, which is a necessary pre-processing step in many tasks of image analysis. Eight algorithms are imhlemented and compared. The performance of the algorithms was analysed frrst; on three sets of differently structured synthetic shaded and shading free irnages, and secondly; on two sets af real microscopical images acguired by two different acguisition set-ups. The results show thut the entropy minimisation (EMl) method outperforms the othermethods in tcrrns of the reduction of true intensity variations and preservation of intensity characteristics of the shading-free images. The strength of EMI is especially apparent when applied to images containing large-scale objects.
Descriptors		IMAGE PROCESSING, COMPUTER-ASSISTED