Title :
Nonlinear adaptive convergence index filters and their characteristics
Author :
Kobatake, Hidefumi ; Jun, Wei ; Yoshinaga, Yukiyasu ; Hagihara, Yoshihiro ; Shimizu, Akinobu
Author_Institution :
Graduate Sch. of Bio-Appl. & Syst. Eng., Tokyo Univ. of Agric. & Technol., Japan
Abstract :
This paper presents nonlinear adaptive filters which are applied to gradient vector fields. The general convergence index of a gradient vector to the pixel of interest or the line of interest is defined and the convergence degree which is the output of the filter is defined as the average of convergence indices over the region of support. Three kinds of filters are proposed. The fundamental characteristics of the proposed filters are given
Keywords :
adaptive filters; convergence; edge detection; filtering theory; nonlinear filters; convergence index; edge detection; gradient vector fields; nonlinear adaptive filters; Adaptive filters; Agricultural engineering; Agriculture; Convergence; Design engineering; Digital filters; Image edge detection; Iris; Nonlinear filters; Systems engineering and theory;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.903598