CLASS OF ROBUST EDGE DETECTORS BASED ON LATIN SQUARES

被引：11

作者：

KADAR, I

KURZ, L

机构：

[1] POLYTECH INST NEW YORK,DEPT ELECT ENGN & ELECTROPHYS,BROOKLYN,NY 11201

[2] GRUMMAN AEROSP CORP,BETHPAGE,NY 11714

来源：

PATTERN RECOGNITION | 1979年 / 11卷 / 5-6期

关键词：

Algorithms; Digital processing; Edge elements; Enhancement; Experimental designs; Image processing; Latin Squares; Masks; Robust detection;

D O I：

10.1016/0031-3203(79)90043-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The theory of Latin Square experimental designs is extended to edge detection of multi-grey level pictorial data. Latin Square designs are realized using mask operations either as a square or in linear forms using ANOVA to estimate the model parameters. The test statistics are based upon the robust F-test and the thresholds are selected by an empirical interactive process. A post hoc comparison method is used to confine the edge element ambiguities to 2-pixel layer thickness in masks greater than 2 × 2 × k. Computer simulations are shown to verify the theory. © 1979.

引用

页码：329 / 339

页数：11