Enhancement of Salt-and-Pepper Noise Corrupted Images Using Fuzzy Filter Design
This investigation presents a fuzzy filtering method for the removal of salt-and-pepper noise of a corrupted image which is caused by the corruption of impulse noise in the record or transmission process. This fuzzy filtering method comprise with a size a
- PDF / 381,433 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 42 Downloads / 258 Views
Abstract This investigation presents a fuzzy filtering method for the removal of salt-and-pepper noise of a corrupted image which is caused by the corruption of impulse noise in the record or transmission process. This fuzzy filtering method comprise with a size adjustable local window which is used to analyze each extreme pixel (0 or 255 for an 8 bits gray-level image) and a fuzzy smoother which can interpolate non-extreme values inside the local window to construct a noiseless center pixel. By the help of the proposed fuzzy filtering method, the center pixel with an extreme value is replaced by the fuzzy interpolation value and enables noisy pixels to be restored smoothly and continuously. From the tough tests, experimental results reveal the fact that salt-and-pepper noises (only for known extreme values 0 and 255) of a corrupted image for different noise corruption densities (from 10 to 90%) can the efficiently removed via the universal interpolation ability of the proposed fuzzy filtering method; meanwhile, the denoised image is free from the blurred effect.
⋅
Keywords Image denoising ability Salt-and-pepper noise window Fuzzy smoother Universal interpolation
⋅
⋅
⋅
Size adjustable
1 Introduction Inevitably, the impulse noises corrupt images due to the following reasons: malfunctioning pixels in camera sensors, fault memory locations in hardware, transmission in a noisy channel, and bit errors in transmission. In real applications, Y.-Y. Chen (✉) ⋅ P.-Y. Chang Department of Systems and Naval Mechatronics Engineering, National Cheng Kung University, Tainan, ROC e-mail: [email protected] C.-T. Lu Department of Information Communication, Asia University, Taichung, Taiwan, ROC e-mail: [email protected]; [email protected]; [email protected]; [email protected] © Springer Nature Singapore Pte Ltd. 2018 N.Y. Yen and J.C. Hung (eds.), Frontier Computing, Lecture Notes in Electrical Engineering 422, DOI 10.1007/978-981-10-3187-8_65
691
692
Y.-Y. Chen et al.
there are two types of impulse noises: the random valued noise and the salt-and-pepper noise. Salt-and-pepper noises which appear with the maximum or the minimum gray levels always seriously corrupt images and significantly deteriorate the quality of an image. How to efficiently remove this kind of impulse noise for the corrupted image becomes an important research task. Recently, many investigations have been contributed for the reconstruction of images contaminated by salt-and-pepper noise [1–10]. In most of these designs, the median and the mean filters were popular for the removal of salt-and-pepper noise because of their good denoising power and computational simplicity. However, some details and edges of the original image cannot be well-restored by the mentioned algorithms when the noise density is over 60%. An adaptive median filter which enabled noisy pixels to be removed by choosing the median value in an adaptive window for each pixel is proposed by Hwang and Hadded [11]. This method performed well at low noise densities but is awful at hi
Data Loading...
