Name
Abstract | ||
|---|---|---|
It is a challenging problem to suppress mixed noise in color images. The traditional bilateral filter can excellently reduce additive noise without destroying image edges and details, but it fails to remove impulsive noise. This paper presents an improved bilateral filtering method, which can simultaneously suppress both impulsive and additive noise. The proposed solution first introduces a new weighting function to the bilateral filtering mechanism, which is experimentally more effective than the traditional Gaussian kernel. Then, either the current pixel or the vector median, instead of always the current pixel itself, is chosen as the base to take part in the bilateral filtering action, which is determined by whether the current pixel is a possible impulse or not. The experimental results show that the proposed solution can simultaneously remove impulsive and additive noise while preserving edge structures, and outperforms other vector filtering methods in terms of both objective evaluation and subjectively visual quality. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1016/j.dsp.2012.06.012 | Digital Signal Processing |
Keywords | Field | DocType |
traditional bilateral filter,improved bilateral filter,color image,proposed solution,vector median,impulsive noise,challenging problem,current pixel,traditional gaussian kernel,mixed noise,additive noise,bilateral filter | Computer vision,Value noise,Median filter,Noise measurement,Salt-and-pepper noise,Image noise,Artificial intelligence,Bilateral filter,Gaussian noise,Mathematics,Gradient noise | Journal |
Volume | Issue | ISSN |
22 | 6 | 1051-2004 |
Citations | PageRank | References |
10 | 0.56 | 18 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lianghai Jin | 1 | 185 | 15.07 |
| Caiquan Xiong | 2 | 18 | 6.77 |
| Enmin Song | 3 | 176 | 24.53 |