International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 07 Issue: 06 | June 2020 www.irjet.net p-ISSN: 2395-0072 © 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 7095 Removing Gaussian Noise Using Mean Filter and Fuzzy Filter P. Gopi Krishna #1 , R. Divya Sai *2 , V. Hema *3 , S. Vasu Pradha *4 , M. Adi Lakshmi *5 # Assistant Professor, Department of Electronics and Communication Engineering, Vignan’s Institute of Engineering for women, Visakhapatnam, Andhra Pradesh, India. ----------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Image filtering is employed to get rid of noise from a picture. Image filtering helps to retrieve the original image from image that is corrupted with noise throughout acquisition and transmission. Noise is associate unwanted signal that is random in nature. So, image filtering aims to get rid of different kinds of noises from a picture. Image filtering also enables us to enhance the images. Mean filter is a linear filter that uses mask over each pixel in a window of an image. It averages all the components within the window and replaces the central pixel with the obtained average value. Hence, the Mean filter is additionally referred to as averaging filter. Fuzzy filter for removing noise from an image is based on fuzzy set theory. It exploits fuzzy rules to determine the gray level of a pixel in a window. This paper presents Image filtering using Mean and fuzzy filters to get rid of Gaussian noise from an image. Further performance can be measured using mean square error and peak signal to noise ratio. 1. INTRODUCTION Image process [2] aims to enhance the image knowledge to suppress the unwanted distortions and to enhance some features of the input image. The output of image process could also be either an image or, a set of characteristics or parameters related to the image. A linear filter is one that can be done with a convolution, which is just the linear sum of values in a sliding window. Linear filters usually blur edges, destroy lines and different fine details present in the image. so to overcome these issues non-linear filters are used. These non-linear filtering techniques [1] preserve signal structure. The mean filter is a linear filter and a fuzzy filter is a non-linear filter. Fuzzy filters will manage the image exactness and ambiguity in several image processing applications efficiently. The rest of the paper is organized as follows:-  In the second section, we described types of noise.  In the third section, we present the method of mean filter.  In the fourth section, we described the fuzzy filter.  In the fifth part, simulation results are discussed.  We conclude and future work in the sixth and seventh part. 2. IMAGE NOISE Image noise [3] is that the random variation of brightness or color data in images created by device and electronic equipment of scanner or camera. Types of noise are the following:  Gaussian noise  Salt-and-pepper noise  Speckle noise  Quantization noise  Film grain  Non-isotropic noise 2.1 Gaussian Noise The Gaussian noise is an image is introduced throughout the acquisition of digital pictures. It is an analytical noise where the probability density function is equal to Gaussian distribution. This noise can be modeled by adding random values to an image Gaussian noise. 2.2 Salt-and-Pepper Noise It is additionally referred to as spike noise. This noise happens once there exists dark pixels in bright region and vice versa. This further indicates that abrupt disturbance in image signals give rise to salt and pepper noise. 2.3 Speckle Noise Speckle noise may be a crude noise that corrupts the components of medical images in general. This noise occurs due to the modeling of the reflectivity function. 3. MEAN FILTER The idea of mean filter [4] is simply to replace each pixel value in an image with the mean (average) value of its neighbors, including itself. This has the impact of eliminating pixel values that are unrepresentative of their surroundings. Mean filtering is usually thought of as a convolution filter. Like other convolution, it is based on