Title :
Fuzzy vector filters using novel distance criteria
Author :
Androutsas, D. ; Plataniotis, K.N. ; Venetsanopoulos, A.N.
Author_Institution :
Dept. of Electr. & Comput. Eng., Toronto Univ., Ont., Canada
Abstract :
A new family of nonlinear filters that use fuzzy membership functions based on different distance measures is proposed for colour image processing. The proposed filters constitute a fuzzy generalization at well known multichannel filters. The principle behind the new filters is explained and comparisons with other nonlinear filters are provided. Colour images corrupted with different type of noises are used to assess the performance of the proposed filters. Simulation results indicate that the new filters offer some flexibility and have excellent performance
Keywords :
filtering theory; fuzzy systems; image colour analysis; image processing; noise; nonlinear filters; colour image processing; distance criteria; distance measures; fuzzy generalization; fuzzy membership functions; fuzzy vector filters; multichannel filters; noise corrupted images; nonlinear filters; performance; simulation results; Color; Colored noise; Electric variables measurement; Filtering; Gaussian noise; Image edge detection; Image processing; Image recognition; Nonlinear filters; Vectors;
Conference_Titel :
Electrical and Computer Engineering, 1995. Canadian Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2766-7
DOI :
10.1109/CCECE.1995.526583
