IMAGE PIXEL CLASSIFICATION BY CHROMATICITY ANALYSIS

被引：14

作者：

ANDREADIS, I ^{[1
]}

BROWNE, MA ^{[1
]}

SWIFT, JA ^{[1
]}

机构：

[1] UNILEVER RES LABS,PORT SUNLIGHT LAB,WIRRAL L62 4XN,CHESHIRE,ENGLAND

来源：

PATTERN RECOGNITION LETTERS | 1990年 / 11卷 / 01期

关键词：

chromaticity; classification; Colour image processing; recognition; segmentation;

D O I：

10.1016/0167-8655(90)90055-7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A technique for colour discrimination based on template matching with tristimulus colour fractions is described. The method overcomes problems of shading and can be used to produce histograms or colour-bin descriptions of images for direct use in recognition or error detection. Alternatively the procedure can be used as a powerful tool for image segmentation. Even with low cost cameras more than 1.000 colours can be reliably discriminated. © 1990.

引用

页码：51 / 58

页数：8