A FUZZY FILTERING MODEL FOR CONTOUR DETECTION

Abstract
Contour detection is the basic property of image processing. Fuzzy Filtering technique is proposed to generate thick edges in two dimensional gray images. Fuzzy logic is applied to extract value for an image and is used for object contour detection. Fuzzy based pixel selection can reduce the drawbacks of conventional methods(Prewitt, Robert). In the traditional methods, filter mask is used for all kinds of images. It may succeed in one kind of image but fail in another one. In this frame work the threshold parameter values are obtained from the fuzzy histogram of the input image. The Fuzzy inference method selects the complete information about the border of the object and the resultant image has less impulse noise and the contrast of the edge is increased. The extracted object contour is thicker than the existing methods. The performance of the algorithm is tested with Peak Signal Noise Ratio(PSNR) and Complex Wavelet Structural Similarity Metrics(CWSSIM).

Authors
T.C.Rajakumar1, S.Arumuga Perumal2 , N.Krishnan3
St. Xavier’s College, Tamil Nadu, India1 , S.T. Hindu College, Tamil Nadu, India2 , M.S. University, Tamil Nadu, India3

Keywords
Contour Detection, Threshold, Histogram, Fuzzy Filtering, Fuzzy Logic
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 1 , Issue: 4 )
Date of Publication :
April 2011

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.