Edge detection in digital images using fuzzy numbers
International Journal of Innovative Computing and Applications
Fingerprint image enhancement using type-2 fuzzy sets
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
| Hi-index | 0.00 |
This paper proposes a fuzzy-based approach toedge detection in gray-level images. The proposed fuzzyedge detector involves two phases - global contrastintensification and local fuzzy edge detection. In the firstphase, a modified Gaussian membership function ischosen to represent each pixel in the fuzzy plane. A globalcontrast intensification operator, containing threeparameters, viz., intensification parameter t, fuzzifier fhand the crossover point xc, is used to enhance the image.The entropy function is optimized to obtain theparameters fh and xc using the gradient descent functionbefore applying the local edge operator in the secondphase. The local edge operator is a generalized Gaussianfunction containing two exponential parameters, 驴 and β.These parameters are obtained by the similar entropyoptimization method. By using the proposed technique, amarked visible improvement in the important edges isobserved on various test images over common edgedetectors.