Vol. 7(23), Jan. 2017, PP. 3225-3234 3225 A Hybrid Method for Edge Detection in Image Corrupted by Impulse Noise Maryamsadat Farhanian 1 and Karim Faez 2 * 1 Faculty of Computer and Information Technology Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran 2 Electrical Engineering Departments, Amirkabir University of Technology *Corresponding Author's E-mail: kfaez@aut.ac.ir Abstract dge detection is a crucial preparatory stage in image processing. The current edge detection methods suffer from the problem of high frailty to noise. In the present paper, a new method for image edge detection in images damaged by Impulse noise introduced. The simple structure of the proposed method is composed of four neural networks, a neuro-fuzzy network and an adaptive median filter. The internal parameters of these networks are adaptively optimized in training through using simple synthetic images that can be generated in a computer. The proposed method is tested on many popular images and the results have been compared with those of the previous edge detectors such as Sobel and Canny. Empirical statistics show that the newly-introduced method presents much better performance than the previous ones and can be benefited in any process of edge detection of the Impulse noise-damaged images. Keywords: neuro-fuzzy network, edge detection, Impulse noise, neural network. 1. Introduction The edge being the most important character of an image is an abrupt change in intensity of an image [1,2]. Image edge is the points with different grey levels and is located mostly between object and object, object and background, area and area [3,4]. Edge detection is one of the most important tasks in the field of image processing and pattern recognition [5]. It plays crucial role in the multimedia and computer vision, image enhancement and image compression and so forth [6]. It is usually the first things done prior to other operations such as image segmentation, boundary detection, object recognition, classification and image registration etc. [7]. Simply put, to be successful in the complicated operation of image processing, the entire attention should be invested in the field of edge detection. With the advent of new developments in the field of mathematics and artificial intelligence (AI), lots of different edge detection methods are on hand, including mathematical morphology, wavelet transformation, Roberts's method, Prewitt method, Sobel method, zero-crossing method, canny methods, LOG method and so on. The most important element decreasing the quality of the edge detection is the noise in the digital image. Digital images are almost always damaged by the Impulse noise (the common image noise, mostly noticed as white or black spots) during image acquisition or transmission. Impulse noise is experienced as a result of the environment features and conditions, quality of sensing elements, and communication channels [8,9]. An important consideration while working with the image processing programs is the image noise removal which should be done first especially because of the noise-sensitiveness condition of later image processing E Article History: Received Date: Sep. 19, 2016 Accepted Date: Dec. 15, 2016 Available Online: Jan. 05, 2017