Abstract | ||
---|---|---|
An effective algorithm for removing impulse noise from corrupted images is presented under the framework of switching median filtering. Firstly, noisy pixels are distinguished by Local Outlier Factor incorporating with Boundary Discriminative Noise Detection (LOFBDND). Then, the directional weighted median filter is adopted to remove the detected impulses by replacing each noisy pixel with the weighted mean of its neighbors in the filtering window. Our noise detection algorithm makes the decision so accurate that the miss detection rate and false detection rate are very low. Extensive simulation results show that our method provides better performance in terms of PSNR and MAE than many other median filters for impulse noise removal. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/LSP.2011.2162583 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
median filters,impulse noise removal,switching median filter,false detection rate,local outlier factor (lof),psnr,switching median filtering,impulse noise,mae,directional weighted median filter,image restoration,local outlier factor,image acquisition,image transmission,corrupted images,miss detection rate,impulse noise detection,lofbdnd,local outlier factor incorporating with boundary discriminative noise detection,switches,noise measurement,noise,indexing terms,median filter,pixel,filtering | Local outlier factor,Median filter,Pattern recognition,Noise measurement,Filter (signal processing),Salt-and-pepper noise,Impulse noise,Pixel,Artificial intelligence,Image restoration,Mathematics | Journal |
Volume | Issue | ISSN |
18 | 10 | 1070-9908 |
Citations | PageRank | References |
10 | 0.52 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Wang | 1 | 382 | 21.84 |
Peizhong Lu | 2 | 230 | 22.46 |