International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 2 Issue: 4 954 – 957 _____________________________________________________________________________________ 954 IJRITCC | April 2014, Available @ http://www.ijritcc.org ______________________________________________________________________________ Edge Detection Technique by Fuzzy Logic CLA and Canny Edge Detector using Fuzzy Image Processing B. Divya II - M.E. (Applied Electronics) Department of ECE Thanthai Periyar Government Institute of Technology Vellore, Tamilnadu, India divyabalaji70@gmail.com Dr. T. K. Shanthi Head,Department of ECE Thanthai Periyar Government Institute of Technology Vellore, Tamilnadu, India tkshanthi@gmail.com T. K. Sethuramalingam Associate Professor, Department of ECE - PG Karpagam College of Engg, Coimbatore, Tamilnadu, India tksethuramalingam@gmail.com Ebin Ephrem Elavathingal I - M.E (Communication Systems), Karpagam College of Engg, Coimbatore, Tamilnadu, India mail2ebine@gmail.com Abstract-Edge detection in an image is an major issue in image processing. Many hidden objects can be identified using edge detection which gives major clue in identifying actual truth behind the images. In this paper, double thresholding method of edge detection along with canny edge detector is used to identify the small objects in an images. Here threshold plays a major role which extracts the clear image from unclear picture. Keywords-Fuzzy logic, Cellular learning automata, Canny edge detector, Thresholding. __________________________________________________*****_________________________________________________ 1 Introduction-Modelling various aspects of human brain is the present artificial intelligence. To deal properly with uncertainities and imprecision which arise from human thinking, mentation cognition and perception, some tools are required. Contrast is one of the most important issues in image processing, pattern recognition and computer vision. Fuzzy logic has been found many applications in image processing. Fuzzy set theory is the useful tool for handling uncertainities related with vagueness/imprecision. Image enhancement is employed to transform an image on basis of psychophysical characteristics on human visual system. To visualize an image to human eyes, the modification of intensity’s distribution inside small regions of the image should be conducted. The basic idea of direct contrast enhancement method is to obtain a criterion of contrast measurement and enhance the image by improving the contrast and increasing the threshold value. Contrast can be measured globally and locally. It is more appropriate to a local contrast when an image contains textural information. The brightness variation is estimated by local image statistics. so when the brightness change in a region is severe, the degree of enhancement is high and enhancement is relatively low. The image storage in bitmap format is not so used in day-to-day applications; even medical images are stored in JPEG format. The fuzzy enhancement is implemented in the fuzzy characteristic plane, with the help of contrast intensification operator. Whenever image is converted from one form to another such as digitizing, scanning, transmitting, storing etc. some of the degradation occurs at the output. Hence output image has to undergo image enhancement which consists of collection of techniques to seek improvement in an image. The edge of the object is reflected by the incontinuity of the gray value. The point of edge also exists between the two neighbors , that is to say, one exists in the inner of a bright region , and the other outside. The other features of the image are all deduced by the foundational feature of the edge and the region. The edge has two features of direction and amplitude: the value of the pixel changes very gently along the edge; and the value of the pixel changes very strongly along the plumb direction of the edge. This kind of acuteness may be hop or sloping. The traditional edge detection is based on the original image. Every pixel of the image is detected by the gray value change of neighbors, and make use of the change of the one-order or two-order directional differential coefficient to detect the edge . This kind of method is called the edge detection partial operator. The kinds of the edge can be divided into two parts: one is called the hop change edge, the gray value of the pixels beside the edge is obviously different; the other is called the housetop edge, it locates in the turning point of the gray value from the increasing to the declining change. Edge detection is one of the most important algorithms in image processing. It plays a fundamental role in higher level processing. Edges