Carbonated soft drink classification based on image analysis and PCA

Quimica nova

Oliveira, Sérgio B. de¹  Pereira, Raquel O.²  Oliveira, Anselmo E. de²  Ribeiro, Keysi de O.²  Godinho, Mariana da S.²  Schimidt, Fernando² 

[1] Centro Federal de Educação Tecnológica de Goiás, Goiânia, Brasil;Universidade Federal de Goiás, Goiânia, Brasil

关键词: PCA;    image analysis;    carbonatedsoft drinks.;   

DOI  :  10.1590/S0100-40422008000600039

学科分类：化学（综合）

来源: Sociedade Brasileira de Quimica

【 摘 要 】

This paper describes an approach for the colour-basedclassification of RGB (red-green-blue) images, acquired using a common scanner,of commercial carbonated soft drinks. Mean histograms of image colour channelswere evaluated for the PCA classification of 29 brands of Guaraná, Cola,and orange flavors. Loadings for principal component axes resulted in differentpatterns for sample grouping on score plots according to RGB histograms. pH,sorbic acid and sucrose measurements were also correlated to the analyzed brandsthrough PCA score plots of the digitalized images.

【 授权许可】

CC BY