You are on page 1of 4

A Random-valued Impulse Noise Detector Using Level Detection

Noritaka YAMASHITA, Munenori OGURA, Jianming LU, Hiroo SEKIYA and Takashi YAHAGI
Graduate School of Science and Technology, Chiba University 1-33, Yayoi-cho, Inage-ku, Chiba, 263-8522 Japan Email: n yamashita@graduate.chiba-u.jp
Abstract In this paper, we propose a new random-valued impulse noise detector from images using level detection. In our method, we use directional windows in order to search a level region in the images. One window whose variation is lowest is selected as a at window from multi directional windows. In a at window, random-valued impulse noise may move to the both ends of order statistics. Therefore, noise detection in selected window is easy. Consequently, the proposed method reduces undetected noise pixels without increasing mis-detections. Extensive simulations indicate that the proposed method performs signicantly better than conventional methods.

x(i,j)

Noise Detector

P(i,j) x(i,j)

x(i,j)

Noise Filter

I. I NTRODUCTION In the image processing, median lters have been widely used for removing impulse noise, since median lters are quite effective for the noise removal and the edge preserving. However, median lters tend to modify both noise pixels and undisturbed good pixels. Recently, switching schemes have been studied for removal impulse noise in images [1]-[3]. These schemes detect whether the current pixel is corrupted by impulse noise at each pixel. Then, ltering is activated for pixels that is detected as noise pixels, while good pixels are kept. As a switching scheme, progressive switching median (PSM) lter [1] was proposed for removal impulse noise. With the PSM lter, both the impulse noise detector and the noise lter are applied progressively. The noise detector detects an impulse noise and outputs a binary ag image. The binary ag image denotes whether pixels are corrupted or not. According to a binary ag image, the noise lter processes to only noise pixels using neighborhood good pixels. Since the noise lter processes according to the binary ag image, the PSM lter performs satisfactorily in removing impulse noise. However, in the case of random-valued impulse noise, the performance of the noise detector is signicantly reduced. If the random-valued impulse noise is located in the middle of order statistics, the noise detector cannot detect the noise. Therefore, the random-valued impulse noise detection is more difcult than the xed-valued impulse noise detection. In this paper, we propose a new random-valued impulse noise detector from images using level detection. In our method, we use directional windows in order to search level region in the images. One window whose variation is lowest is selected as a at window from multi directional windows. In a at window, random-valued impulse noise may move to the both ends of order statistics. Therefore, the noise detector

Input
Fig. 1. Structure of the PSM lter.

Output

can detect the noise in the selected window. Consequently the proposed method reduces undetected noise pixels without increasing mis-detection. Extensive simulations indicate that the proposed method performs signicantly better than conventional methods. II. PSM FILTER [1] A structure of the PSM lter is shown in Fig.1. The PSM lter consists of the noise detector and the noise lter. In the noise detector, the current pixel x(i, j) is judged whether it is corrupted by an impulse noise or not using neighborhood pixels. First, a median value of neighborhood pixels m(i, j) is obtained. Next, a binary ag image P (i, j) is given by P (i, j) = 1 0 |x(i, j) m(i, j)| TD otherwise (1)

where TD is a threshold of the noise detection. P (i, j) = 1 means x(i, j) is corrupted by an impulse noise. On the other hand, P (i, j) = 0 means x(i, j) may be a good pixel. If TD is small, almost noises are detected. However, good pixels are regarded as a noise pixel. On the other hand, in case that TD is large, the mis-detection is decreased with increasing the undetection. In the noise lter, x(i, j) is processed based on the binary ag image. The noise lter processes to only noise pixels using neighborhood good pixels. Since the noise lter processes based on the binary ag image, the PSM lter performs satisfactorily in removing impulse noise. Therefore, the performance of the noise lter depends on the binary ag image.

0-7803-8834-8/05/$20.00 2005 IEEE.

6292

Window 0 flat 0 x(i,j) Input Window1 flat1 Flat Window Decision Wf Noise Detector

W0
P(i,j) Output

Windown

Window Evaluation

...

flat

W3

Fig. 2.

Topology of proposed method by using level detection.

W1

W2

W4

However, in the case of random-valued impulse noise, the performance of the noise detector is signicantly reduced. If the random-valued impulse noise is located in the middle of order statistics, the noise detector cannot detect the noise and the undetection is increased. If TD is set to small in order to decrease the undetection, the mis-detection is increased. Therefore, the random-valued impulse noise detection is more difcult than the xed-valued impulse noise detection. III. P ROPOSED M ETHOD In this paper, a new random-valued impulse noise detector from images is proposed. The input signal x(i, j) is given by x(i, j) = x0 (i, j) : probability 1 q h : probability q (2)
W7

W5

W6

W8

:process pixel
Fig. 3. Multi window used in this paper.

where (i, j) denote the pixel coordinates of an image, x0 (i, j) is the original image, q is impulse noise ratio, and h is uniformly distributed within [0,255]. A topology of the proposed impulse noise detector is shown in Fig.2. The detector consists of the window evaluation, the at window decision and the noise detector. A. Directional window In our method, we use directional windows in order to search a level region in the images. One window whose variation is lowest selected as a at window from multi directional windows includes a at region. In the noise detector, an impulse noise is detected using the at window. In a at window, the random-valued impulse noise may move to the both ends of order statistics even if the noise is located in the middle of order statistics. Therefore, the noise detector can detect the random-valued impulse noise. In our method, we use some directional windows for searching the at region. Directional windows Wn (n = 1, 2, , 8) are shown in Fig.3. The size of the directional window is 25. Since we use multi windows with various direction, searching the at region is easy at each pixel. Consequently, the performance of the noise detector is improved. B. Flat window decision In window evaluation, rst, signals in the window Wn are n n n n n sorted and rn = {r1 , r2 , , rm } (ri ri+1 ) is obtained.

Next, the pair of k and l is searched according to


n n rl rk > T h (1 k < l m) n n rl1 rk T h

(3)

where T h is a threshold for at decision.The k for maximum (l k) is searched from these pair. The intensity of at is dened by f latn = l k (4) where f latn is used to select the at window. If f latn is small, Wn includes the edge or impulse noises. On the other hand, in case that f latn is large, Wn includes a at region. Next, in the at window decision, the window used to detect impulse noise is dened by if f latn M Wn for maximum f latn (5) Wf = if f latn < M W0 for maximum f latn where M is threshold in order to allow that Wn is the at window. If f latn < M , there is no at region in Wn . In this case, since we use pixel at the neighborhood of the current pixel, the noise detector uses the window W0 . Here, if Wn includes the at region, TD can be set to small in order to reduce undetected noise pixels. Since the variation of Wn is low in the at window, the noise detector generates few mis-detection for small TD . On the other hand, in case

6293

30 25 20 Th 15 10 5 0.8 0 5

Mis-Detected Ratio [%]

0.2

0.4

0.6

0.8

30 25 20 15 0.8 10 0.6 5 0 5 6 7 M Th

0.8

0.6

0.4 0.2

6 5 4 3 2 1 0 10 20

PSM[1] FW

Airplane Barbara Boat Lenna Text

7 M

(a) Boat, q = 10%


30 25 20 Th 15 10 5 0 5 6 7 M 8 0.6 9 0.8 Th 0.2 0.4 0.6 0.8 30 25 0.6 20 15 10 5 0 0.8

(b) Boat, q = 40%


0.8 0.6 0.4 0.2

Noise Ratio q [%]

30

40

Fig. 5.

The mis-detected ratio of the PSM and the FW.

14
5 6

(c) Lenna, q = 10%


Fig. 4.

(d) Lenna, q = 40%

Undetected Ratio [%]

7 M

12 10 8 6 4 2 0 10

Relation among M ,T h and normalized PSNR

Airplane Barbara Boat Lenna Text

PSM[1] FW

that Wn has no at region, TD should be set to large in order to reduce mis-detection. If TD is set to small in non-at, misdetection is increased. IV. S IMULATION RESULTS The performance of the proposed method has been evaluated by the simulations. In the simulation, windows of Fig.3 are used to search a at region. And, the noise detector is carried out by the median-based impulse noise detector[1]. TD is set to 20 for at region and 50 for no at region. Boat, Lenna, Airplane, Barbara and T ext are used as processing images(256 256 , 8bits). This images is corrupted by random-valued impulse noise (q = 10 40%). The performance of noise detection is quantitatively measured by the mis-detected ratio and the undetected ratio. And the performance of restoration is quantitatively measured by the peak signal to noise ratio(PSNR). In our method, two threshold T h and M are used to decide a at window. We rst study the effects of T h and M on the performance of impulse noise detection. Fig.4 shows the normalized PSNR of ltering Boat and Lenna corrupted by the random-valued impulse noise (q = 10, 40%). In Fig.4(a)(c), the PSNR depends on T h for M = 5, 6. For low probability impulse noise ratio, the window includes few impulse noises. If M is set to small, non-at is regarded as a at region. Therefore, mid-detection is increased, and the performance of the restoration is reduced. In Fig.4(b)(d), the PSNR obtained for M = 8, 9 is low. Since the window includes many impulse noises for high impulse noise ratio, almost windows is judged to be Wf = W0 . Therefore, better results cannot be obtained for M = 8, 9. On the other hand, in case that M is small, T h obtaining better PSNR exists. If T h is smaller than optimal threshold, the window including at

20

30

40

Noise Ratio q [%]


Fig. 6. The undetected ratio of the PSM and the FW.

region is judged as no at window. Therefore, the performance of restoration is reduced. On the other hand, in case that T h is larger than optimal threshold, no at region is regarded as at region. Thus, the PSNR is declined. In Fig.4, we set T h = 15 and M = 7 in order to adapt various noise ratio. The performance of the proposed method is compared with that of the PSM lter[1]. The parameter of the PSM lter is selected to obtain better performance for different cases. Here, the proposed method is named the at window (FW) method. Fig.5 shows the mis-detected ratio of the PSM and the FW. And, Fig.6 shows the undetected ratio. In Fig.5, the mis-detected ratio of the FW and that of the PSM almost equivalent. In Fig.6, the undetected ratio of the FW is better than that of the PSM for various noise ratio and images. That is because random-valued impulse noise are detected using a at window searched from multi directional windows. Therefore, the undetected ratio is reduced without increasing the misdetected ratio. Next, the FW is compared with the PSM in terms of ltering results. In this simulation, images are processed using each binary ag image with the noise lter[1]. Fig.7 shows the PSNR of ltering images corrupted by random-valued impulse noise with different noise ratios. In Fig.7, the FW exceeds

6294

35 32
PSM[1] FW Airplane Barbara Boat Lenna Text

PSNR [dB ]

29 26 23 20 10 20 30

Noise Ratio q [%]

40

Fig. 7. Performance evaluation of the PSM and the FW in ltering images corrupted by random-valued impulse noise.

(a)Original

(b)Noisy

the PSM in PSNR. Since the FW reduces undetected noise pixel without increasing mis-detection, the performance of the noise ltering is improved. Fig.8 shows the results of ltering Airplane corrupted by the random-valued impulse noise (q = 10%). And, Fig.9 shows the results of ltering Boat corrupted by the random-valued impulse noise (q = 40%). In Fig.8(c) and Fig.9(c), impulse noises remain in resultant images by the PSM. Furthermore, in Fig.9(c), the PSM provides inferior performance in edge preservation. Since the detection of the random-valued impulse noise is difcult, impulse noise remains in resultant images. In Fig.8(d) and Fig.9(d), better results have been achieved by the FW with more effective noise rejection and edge preservation. That is because the performance of the noise detection is improved by searching at region. V. C ONCLUSION In this paper, we have proposed a new random-valued impulse noise detector from images using level detection. In our method, one window whose variation is lowest is selected as a at window. In a at window, random-valued impulse noise may move to the both ends of order statistics. Therefore, the performance of noise detection is increased. In the simulation, the proposed method has demonstrated superior performance in detecting impulse noise. Especially, it is note worthy that the proposed method has shown the noticeable difference from other methods in the noise detected rate as well as the image quality. R EFERENCES
[1] Z. Wang and D. Zhang, Progressive switching median lter for the removal of impulse noise from highly corrupted images, IEEE Trans. Circuits Syst. II, Analog and Digit. Signal Process. , Vol. 46, No. 1, pp. 78-80, Jan. 1999. [2] T. Sun and Y. Neuvo, Detail-preserving median based lters in image processing, Pattern Recognit. Lett., Vol. 15, pp. 341-347, April 1994. [3] T. Chen, K.-K. Ma and L.-H. Chen, Tri-state median lter for image denoising, IEEE Trans. Image Processing, Vol. 8, pp. 1834-1838, Dec. 1999.

(c)PSM
Fig. 8.

(d)FW

Restoration images (Airplane, q = 10%).

(a)Original

(b)Noisy

(c)PSM
Fig. 9.

(d)FW

Restoration images (Boat, q = 40%).

6295

You might also like