COLOR IMAGE SEGMENTATION AND LABELING THROUGH MULTIEDIT-CONDENSING

被引：15

作者：

FERRI, F

VIDAL, E

机构：

[1] UNIV POLITECN VALENCIA,DEPT SISTEMAS INFORMAT & COMPUTAC,CAMINO DE VERA S-N,E-46020 VALENCIA,SPAIN

[2] UNIV VALENCIA,DEPT INFORMAT & ELECTR,VALENCIA,SPAIN

来源：

PATTERN RECOGNITION LETTERS | 1992年 / 13卷 / 08期

关键词：

NEAREST NEIGHBOR RULE; MULTIEDIT-CONDENSING; SCENE SEGMENTATION; PATTERN RECOGNITION; ROBOTICS;

D O I：

10.1016/0167-8655(92)90091-D

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new method is proposed for detecting and locating objects of interest within a colour scene under verv strong variabilities in lighting conditions, object shape and pigmentation. The method is based on Nearest Neighbour classification and Multiedit-Condensing techniques and is applied to implement the vision subsystem of a robotic citric harvesting device. Experiments and results are reported showing the effectiveness of the method and illustrating its appropriateness to the proposed task.

引用

页码：561 / 568

页数：8

共 12 条

[1]

Aho A. V., 1974, DESIGN ANAL COMPUTER

[2]

AIBAR P, 1990, SPEECH RECOGNITION U

[3]

BLANZ WE, 1989, ADV MACHINE VISION

[4] ON THE EDITING RATE OF THE MULTIEDIT ALGORITHM [J].

DEVIJVER, PA .

PATTERN RECOGNITION LETTERS, 1986, 4 (01) :9-12

[5]

Devijver PA, 1982, PATTERN RECOGNITION

[6]

Duda R. O., 1973, PATTERN CLASSIFICATI, V3

[7]

GOWDA KC, 1979, IEEE T INFORM THEORY, V125, P488

[8] CONDENSED NEAREST NEIGHBOR RULE [J].

HART, PE .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1968, 14 (03) :515-+

[9]

OTHA Y, 1980, COMPUTER GRAPHICS IM, V13, P222

[10]

SAMMET H, 1986, P COMPUTER VISION PA

← 1 2 →