Diminishing Noise Using Adaptive Fuzzy Switching Median Filter

This research work presents a simple, yet efficient way to remove noise from digital images. The method comprises three phases: the first phase is to detect the noise in the image. In this phase, based on only the intensity values, the pixels are roughly divided into two classes, which are “noise-free pixel” and “noise pixel”. Then, the second phase is to remove the impulse noise from the image. In this phase, only the “noise-pixels” are processed. The “noise free pixels” are copied directly to the output image. Then, the third phase, in which adaptive fuzzy inference system is used for giving the choice to the user. In this research paper, present a novel method for the removal of noise from digital images. The proposed operator is a hybrid filter obtained by appropriately combining a low, median and high pass filter and adaptive fuzzy switching median filter. The noise is exactly estimated through the proposed operator. The distinctive feature of the proposed operator is that it offers well line, edge, detail and texture preservation performance while, at the same time, effectively removing noise from the input image. AFSM filter is capable of removing all kind of noise. The internal parameters of the FIS are adaptively optimized by training. This proposed method is suitable to be implemented in consumer electronics products such as digital televisions, cameras, etc. INTRODUCTION From ancient times to now-a-days, the image processing techniques have been well developed, but there are still some bottlenecks on which researchers have their focus. Unfortunately, during image acquisition, transmission and storage, many types of distortion contaminate the quality of received images. Digital images are corrupted by many types of noises such as malfunctioning pixels in camera sensors, faulty memory locations in hardware or transmission of image in a noisy channel and some other causes also. Noise affect the accuracy of many image processing applications such as image segmentation, image classification, edge extraction, image compression, etc,. Many image processing algorithms cannot work well in noisy environment. Specifically for removal of noise from an input image there are several filters that can be considered as the state-ofart methods given their impressive performance. For instance, low, high and median pass filter is one of the orderstatistic filters, which falls in the group of non-linear filter. Median pass filter is used in variety of application to remove impulse noise from corrupted images [11], [12]. But the conventional Median pass filter method can treat all the pixels in the image equally. This will result the elimination of fine details such as thin lines and corner, blurring and distortion in the image. So, to overcome this problem, various types of filters are come into picture such as Switching median filter, Center weighted median filter, rank ordered mean filter, noise detection based median filter [1]-[10]. In paper [1], CAFSM filter is capable of filtering all kinds of impulse noise the random-valued and/or fixed-valued impulse noise models. In [2] paper presents an efficient way to remove impulse noise from digital images. The experimental result shows that the average processing time to process an image that contains noise percentage 95%, it takes less than 2.7 seconds to process the image. In [3] paper presents a novel method for the suppression of Random-Valued Impulsive Noise from corrupted images. The noise free intensity values can be restored by using Triangle-Based Linear Interpolation. In paper [4], use soft computing techniques, a noisy image is used as input data; a performance index is then evaluated by considering the mean square error (MSE) between the filtered data and the original noise-free image. Abreu et al. [6] propose an efficient nonlinear algorithm to suppress impulse noise from highly corrupted images while preserving details and features. In [8] the center weighted median filter, which a weighted median filter is giving more weight only to the central value of each window. This filter can preserve image details while suppressing additive white and/or impulsive-type noise. In [10] Multi-dimensional Weighted [Bhargava, 2(3): March, 2015] ISSN: 2349-6193