LUM PROCESSOR WITH NEURAL DECISION
2006 ◽
Vol 20
(05)
◽
pp. 747-762
Keyword(s):
This paper focuses on impulsive noise filtering and outliers rejection in gray-scale images. The proposed method combines neural networks, lower-upper-middle (LUM) smoothers and adaptive switching operations to produce a high-quality enhanced image. Extensive experimentation reported in this paper indicates that the proposed method is sufficiently robust, achieves an excellent balance between noise suppression and signal-detail preservation, and outperforms some well-known filters both subjectively and objectively.
2005 ◽
pp. 679-684
◽