Nonlinear Adaptive Convergence Index Filters and Their Characteristics

Hidefumi Kobatake; Wei Jun; Yoshihiro Hagihara; Akinobu Shimizu; Yukiyasu Yoshinaga

doi:10.1109/ICPR.2000.903598

Pattern Recognition, International Conference on

Nonlinear Adaptive Convergence Index Filters and Their Characteristics

Year: 2000, Volume: 3, Pages: 3526

DOI Bookmark: 10.1109/ICPR.2000.903598

Authors

Hidefumi Kobatake, Tokyo University of Agriculture and Technology
Wei Jun, Tokyo University of Agriculture and Technology
Yoshihiro Hagihara, Tokyo University of Agriculture and Technology
Akinobu Shimizu, Tokyo University of Agriculture and Technology
Yukiyasu Yoshinaga, Kyushu Institute of Design

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.

Like what you’re reading?

Already a member?

Get this article FREE with a new membership!